{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:44:09Z","timestamp":1776116649761,"version":"3.50.1"},"reference-count":104,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100024370","name":"Governo Italiano Ministero dell'Istruzione dell'Universita e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100024370","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019771","name":"European Union's Research and Innovation","doi-asserted-by":"publisher","award":["HE 101070284"],"award-info":[{"award-number":["HE 101070284"]}],"id":[{"id":"10.13039\/100019771","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019771","name":"European Union's Research and Innovation","doi-asserted-by":"publisher","award":["HE 101189771"],"award-info":[{"award-number":["HE 101189771"]}],"id":[{"id":"10.13039\/100019771","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data & Knowledge Engineering"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.datak.2026.102596","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:34:05Z","timestamp":1773992045000},"page":"102596","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["How good are LLMs in disambiguating entities in tabular data? A comprehensive study"],"prefix":"10.1016","volume":"164","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0140-3318","authenticated-orcid":false,"given":"Federico","family":"Belotti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Cremaschi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Dadda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Avogadro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Palmonari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.datak.2026.102596_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.datak.2024.102324","article-title":"Large language models: Expectations for semantics-driven systems engineering","volume":"152","author":"Buchmann","year":"2024","journal-title":"Data Knowl. Eng."},{"issue":"10","key":"10.1016\/j.datak.2026.102596_b2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1145\/2629489","article-title":"Wikidata: a free collaborative knowledgebase","volume":"57","author":"Vrande\u010di\u0107","year":"2014","journal-title":"Commun. ACM"},{"key":"10.1016\/j.datak.2026.102596_b3","series-title":"ISWC\/ASWC","article-title":"DBpedia: A nucleus for a web of open data","author":"Auer","year":"2007"},{"issue":"1","key":"10.1016\/j.datak.2026.102596_b4","first-page":"1:1","article-title":"KG2Tables: A Domain-Specific Tabular Data Generator to Evaluate Semantic Table Interpretation Systems","volume":"3","author":"Abdelmageed","year":"2025","journal-title":"Trans. Graph Data Knowl."},{"key":"10.1016\/j.datak.2026.102596_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.websem.2022.100761","article-title":"From tabular data to knowledge graphs: A survey of semantic table interpretation tasks and methods","volume":"76","author":"Liu","year":"2023","journal-title":"J. Web Semant."},{"key":"10.1016\/j.datak.2026.102596_b6","series-title":"The Semantic Web\u2013ISWC 2016: 15th International Semantic Web Conference, Kobe, Japan, October 17\u201321, 2016, Proceedings, Part I 15","first-page":"446","article-title":"Semantic labeling: a domain-independent approach","author":"Pham","year":"2016"},{"key":"10.1016\/j.datak.2026.102596_b7","series-title":"Proceedings of the 2022 International Conference on Management of Data","first-page":"1493","article-title":"Annotating columns with pre-trained language models","author":"Suhara","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b8","series-title":"Multi-Source, Multilingual Information Extraction and Summarization","first-page":"93","article-title":"Entity linking: Finding extracted entities in a knowledge base","author":"Rao","year":"2013"},{"key":"10.1016\/j.datak.2026.102596_b9","doi-asserted-by":"crossref","unstructured":"R. Avogadro, M. Ciavotta, F. De Paoli, M. Palmonari, D. Roman, Estimating Link Confidence for Human-in-the-Loop Table Annotation, in: 2023 IEEE\/WIC International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT, 2023, pp. 142\u2013149.","DOI":"10.1109\/WI-IAT59888.2023.00025"},{"key":"10.1016\/j.datak.2026.102596_b10","series-title":"The Semantic Web","first-page":"514","article-title":"SemTab 2019: Resources to benchmark tabular data to knowledge graph matching systems","author":"Jim\u00e9nez-Ruiz","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b11","series-title":"Survey on semantic interpretation of tabular data: Challenges and directions","author":"Cremaschi","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b12","series-title":"Technologies and Applications for Big Data Value","first-page":"19","article-title":"Supporting semantic data enrichment at scale","author":"Ciavotta","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.datak.2024.102341","article-title":"An interactive approach to semantic enrichment with geospatial data","volume":"153","author":"De Paoli","year":"2024","journal-title":"Data Knowl. Eng."},{"key":"10.1016\/j.datak.2026.102596_b14","series-title":"ISWC","first-page":"345","article-title":"Semantically-enabled optimization of digital marketing campaigns","author":"Cutrona","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b15","series-title":"CEUR Workshop Proceedings","first-page":"5","article-title":"Building a canonical register of public sector entities: Semantic linking of procurement data at scale","volume":"Vol. 4085","author":"Avogadro","year":"2025"},{"key":"10.1016\/j.datak.2026.102596_b16","doi-asserted-by":"crossref","first-page":"129995","DOI":"10.1109\/ACCESS.2025.3590135","article-title":"From code to concept: A semantic approach to AI innovation discovery in open source software repositories","volume":"13","author":"Novalija","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.datak.2026.102596_b17","series-title":"SemTab@ ISWC","first-page":"68","article-title":"MAGIC: Mining an augmented graph using INK, starting from a CSV.","author":"Steenwinckel","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b18","series-title":"ESWC Demo Papers","first-page":"107","article-title":"DAGOBAH-UI: a new hope for semantic table interpretation","author":"Sarthou-Camy","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b19","series-title":"European Conference on Service-Oriented and Cloud Computing","first-page":"33","article-title":"SemT: A framework for enhancing tabular data through enrichment-as-a-service","author":"Alidu","year":"2025"},{"issue":"1","key":"10.1016\/j.datak.2026.102596_b20","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1145\/3542700.3542709","article-title":"Turl: Table understanding through representation learning","volume":"51","author":"Deng","year":"2022","journal-title":"ACM SIGMOD Rec."},{"key":"10.1016\/j.datak.2026.102596_b21","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b22","series-title":"TableLlama: Towards open large generalist models for tables","author":"Zhang","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b23","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b24","unstructured":"J. Wei, M. Bosma, V. Zhao, K. Guu, A.W. Yu, B. Lester, N. Du, A.M. Dai, Q.V. Le, Finetuned Language Models are Zero-Shot Learners, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.datak.2026.102596_b25","series-title":"CEUR Workshop Proceedings","first-page":"1","article-title":"Results of SemTab 2023","volume":"3557","author":"Hassanzadeh","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b26","series-title":"International Semantic Web Conference","first-page":"425","article-title":"Tabel: Entity linking in web tables","author":"Bhagavatula","year":"2015"},{"key":"10.1016\/j.datak.2026.102596_b27","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"4163","article-title":"TinyBERT: Distilling BERT for natural language understanding","author":"Jiao","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b28","series-title":"LongLoRA: Efficient fine-tuning of long-context large language models","author":"Chen","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112447","article-title":"Feature\/vector entity retrieval and disambiguation techniques to create a supervised and unsupervised semantic table interpretation approach","volume":"304","author":"Avogadro","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.datak.2026.102596_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112447","article-title":"Feature\/vector entity retrieval and disambiguation techniques to create a supervised and unsupervised semantic table interpretation approach","volume":"304","author":"Avogadro","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"4","key":"10.1016\/j.datak.2026.102596_b31","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1007\/s00778-023-00824-x","article-title":"A multi-facet analysis of bert-based entity matching models","volume":"33","author":"Paganelli","year":"2024","journal-title":"VLDB J."},{"key":"10.1016\/j.datak.2026.102596_b32","series-title":"International Conference on Human-Computer Interaction","first-page":"182","article-title":"Applications of large language models (LLMs) in business analytics\u2013exemplary use cases in data preparation tasks","author":"Nasseri","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b33","unstructured":"T. Wang, X. Chen, H. Lin, X. Chen, X. Han, L. Sun, H. Wang, Z. Zeng, Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching, in: Proceedings of the 31st International Conference on Computational Linguistics, 2025, pp. 96\u2013109."},{"key":"10.1016\/j.datak.2026.102596_b34","series-title":"Proceedings of the 4th New Frontiers in Summarization Workshop","first-page":"1","article-title":"Is chatGPT a good NLG evaluator? A preliminary study","author":"Wang","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b35","unstructured":"R. Kirk, I. Mediratta, C. Nalmpantis, J. Luketina, E. Hambro, E. Grefenstette, R. Raileanu, Understanding the Effects of RLHF on LLM Generalisation and Diversity, in: The Twelfth International Conference on Learning Representations, 2024."},{"issue":"19","key":"10.1016\/j.datak.2026.102596_b36","first-page":"21841","article-title":"Can LLM replace stack overflow? A study on robustness and reliability of large language model code generation","volume":"38","author":"Zhong","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"17","key":"10.1016\/j.datak.2026.102596_b37","first-page":"19615","article-title":"LLMEval: A preliminary study on how to evaluate large language models","volume":"38","author":"Zhang","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.datak.2026.102596_b38","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"15696","article-title":"Large language models struggle to learn long-tail knowledge","volume":"vol. 202","author":"Kandpal","year":"2023"},{"issue":"1\u20132","key":"10.1016\/j.datak.2026.102596_b39","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.14778\/1920841.1921005","article-title":"Annotating and searching web tables using entities, types and relationships","volume":"3","author":"Limaye","year":"2010","journal-title":"Proc. VLDB Endow."},{"issue":"6","key":"10.1016\/j.datak.2026.102596_b40","first-page":"921","article-title":"Effective and efficient semantic table interpretation using tableminer+","volume":"8","author":"Zhang","year":"2017","journal-title":"Semant. Web"},{"key":"10.1016\/j.datak.2026.102596_b41","series-title":"SemTab@ ISWC","first-page":"1","article-title":"ADOG-annotating data with ontologies and graphs.","volume":"Vol. 2019","author":"Oliveira","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b42","series-title":"The Semantic Web \u2013 ISWC 2019","first-page":"364","article-title":"Extracting novel facts from tables for knowledge graph completion","author":"Kruit","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b43","unstructured":"B. Steenwinckel, G. Vandewiele, F. De Turck, F. Ongenae, Csv2kg: Transforming Tabular Data into Semantic Knowledge, SemTab, ISWC Challenge, 2019."},{"key":"10.1016\/j.datak.2026.102596_b44","series-title":"SemTab@ ISWC","first-page":"25","article-title":"Entity linking to knowledge graphs to infer column types and properties.","volume":"Vol. 2019","author":"Thawani","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b45","series-title":"SemTab@ ISWC","first-page":"15","article-title":"MantisTable: an automatic approach for the semantic table interpretation.","volume":"Vol. 2019","author":"Cremaschi","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b46","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.future.2020.05.019","article-title":"A fully automated approach to a complete semantic table interpretation","volume":"112","author":"Cremaschi","year":"2020","journal-title":"Future Gener. Comput. Systems"},{"key":"10.1016\/j.datak.2026.102596_b47","series-title":"SemTab@ ISWC","first-page":"75","article-title":"MantisTable SE: an efficient approach for the semantic table interpretation.","author":"Cremaschi","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b48","series-title":"SemTab@ ISWC","first-page":"27","article-title":"DAGOBAH: Enhanced scoring algorithms for scalable annotations of tabular data.","author":"Huynh","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b49","series-title":"CEUR Workshop Proceedings","first-page":"59","article-title":"Lexma: Tabular data to knowledge graph matching using lexical techniques","volume":"2775","author":"Tyagi","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b50","series-title":"CEUR Workshop Proceedings","first-page":"17","article-title":"Bbw: Matching CSV to wikidata via meta-lookup","volume":"Vol. 2775","author":"Shigapov","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b51","series-title":"SemTab@ ISWC","first-page":"79","article-title":"MantisTable v: A novel and efficient approach to semantic table interpretation.","author":"Avogadro","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b52","series-title":"SemTab@ ISWC","first-page":"42","article-title":"JenTab meets SemTab 2021\u2019s new challenges.","author":"Abdelmageed","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b53","series-title":"SemTab@ ISWC","first-page":"19","article-title":"DAGOBAH: Table and graph contexts for efficient semantic annotation of tabular data","author":"Huynh","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.websem.2022.100733","article-title":"LinkingPark: An automatic semantic table interpretation system","volume":"74","author":"Chen","year":"2022","journal-title":"J. Web Semant."},{"key":"10.1016\/j.datak.2026.102596_b55","series-title":"Semantic Web Challenge on Tabular Data to Knowledge Graph Matching","article-title":"s-elBat: a semantic interpretation approach for messy table-s","volume":"Vol. 3320","author":"Cremaschi","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b56","unstructured":"Z. Syed, T. Finin, V. Mulwad, A. Joshi, Exploiting a web of semantic data for interpreting tables, in: Proceedings of the Second Web Science Conference, Vol. 5, 2010."},{"key":"10.1016\/j.datak.2026.102596_b57","series-title":"5th International Conference on Web Intelligence, Mining and Semantics","first-page":"10:1","article-title":"Matching HTML tables to DBpedia","author":"Ritze","year":"2015"},{"key":"10.1016\/j.datak.2026.102596_b58","series-title":"The Semantic Web \u2013 ISWC 2017","first-page":"260","article-title":"Matching web tables with knowledge base entities: From entity lookups to entity embeddings","author":"Efthymiou","year":"2017"},{"key":"10.1016\/j.datak.2026.102596_b59","doi-asserted-by":"crossref","unstructured":"J. Chen, E. Jim\u00e9nez-Ruiz, I. Horrocks, C. Sutton, Colnet: Embedding the semantics of web tables for column type prediction, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 29\u201336.","DOI":"10.1609\/aaai.v33i01.330129"},{"key":"10.1016\/j.datak.2026.102596_b60","series-title":"Mtab: matching tabular data to knowledge graph using probability models","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b61","series-title":"SemTab@ ISWC","first-page":"86","article-title":"MTab4Wikidata at SemTab 2020: Tabular data annotation with wikidata.","volume":"Vol. 2775","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b62","series-title":"SemTab@ ISWC","first-page":"92","article-title":"SemTab 2021: Tabular data annotation with mtab tool.","author":"Nguyen","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b63","series-title":"SemTab@ ISWC","first-page":"49","article-title":"Semantic table interpretation using LOD4all.","volume":"Vol. 2019","author":"Morikawa","year":"2019"},{"key":"10.1016\/j.datak.2026.102596_b64","series-title":"SemTab@ ISWC","first-page":"9","article-title":"AMALGAM: making tabular dataset explicit with knowledge graph.","author":"Azzi","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b65","series-title":"SemTab@ ISWC","article-title":"Linkingpark: An integrated approach for semantic table interpretation","author":"Chen","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b66","series-title":"SemTab@ ISWC","first-page":"40","article-title":"JenTab: Matching tabular data to knowledge graphs.","author":"Abdelmageed","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b67","series-title":"SemTab@ ISWC","first-page":"54","article-title":"Kepler-aSI at SemTab 2021.","author":"Baazouzi","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b68","article-title":"From heuristics to language models: A journey through the universe of semantic table interpretation with DAGOBAH","author":"Huynh","year":"2022","journal-title":"SemTab"},{"key":"10.1016\/j.datak.2026.102596_b69","series-title":"ISWC 2022, October 23\u201327, 2022","first-page":"498","article-title":"Radar station: Using KG embeddings for semantic table interpretation and entity disambiguation","author":"Liu","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b70","series-title":"ISWC Posters & Demonstrations Track","first-page":"25","article-title":"T2LD: Interpreting and representing tables as linked data","author":"Mulwad","year":"2010"},{"key":"10.1016\/j.datak.2026.102596_b71","series-title":"Proceedings of the Web Conference 2020","first-page":"1298","article-title":"Novel entity discovery from web tables","author":"Zhang","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b72","series-title":"AAAI 2011","article-title":"Automatically generating government linked data from tables","author":"Mulwad","year":"2011"},{"key":"10.1016\/j.datak.2026.102596_b73","series-title":"The Semantic Web \u2013 ISWC 2013","first-page":"363","article-title":"Semantic message passing for generating linked data from tables","author":"Mulwad","year":"2013"},{"key":"10.1016\/j.datak.2026.102596_b74","series-title":"The Semantic Web - ISWC 2015","first-page":"425","article-title":"TabEL: Entity linking in web tables","author":"Bhagavatula","year":"2015"},{"key":"10.1016\/j.datak.2026.102596_b75","series-title":"SemTab@ ISWC","first-page":"32","article-title":"GBMTab: A graph-based method for interpreting noisy semantic table to knowledge graph.","author":"Yang","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b76","first-page":"1","article-title":"Unifying large language models and knowledge graphs: A roadmap","author":"Pan","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.datak.2026.102596_b77","doi-asserted-by":"crossref","first-page":"50","DOI":"10.14778\/3421424.3421431","article-title":"Deep entity matching with pre-trained language models","volume":"14","author":"Li","year":"2021","journal-title":"Proc. the VLDB Endow."},{"key":"10.1016\/j.datak.2026.102596_b78","series-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020","article-title":"ELECTRA: pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b79","series-title":"CEUR Workshop Proceedings","first-page":"21","article-title":"TorchicTab: Semantic table annotation with wikidata and language models","volume":"3557","author":"Dasoulas","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b80","series-title":"Column type annotation using ChatGPT","author":"Korini","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b81","series-title":"Semantic Web Challenge on Tabular Data to Knowledge Graph Matching","article-title":"SOTAB: The WDC schema. org table annotation benchmark","volume":"Vol. 3320","author":"Korini","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b82","series-title":"Using ChatGPT for entity matching","author":"Peeters","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b83","series-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023"},{"issue":"1","key":"10.1016\/j.datak.2026.102596_b84","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1038\/s41746-024-01024-9","article-title":"CancerGPT for few shot drug pair synergy prediction using large pretrained language models","volume":"7","author":"Li","year":"2024","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.datak.2026.102596_b85","series-title":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","first-page":"645","article-title":"Table meets LLM: Can large language models understand structured table data? A benchmark and empirical study","author":"Sui","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b86","unstructured":"K. Kong, J. Zhang, Z. Shen, B. Srinivasan, C. Lei, C. Faloutsos, H. Rangwala, G. Karypis, OpenTab: Advancing Large Language Models as Open-domain Table Reasoners, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.datak.2026.102596_b87","series-title":"TabSQLify: Enhancing reasoning capabilities of LLMs through table decomposition","author":"Nahid","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b88","unstructured":"Z. Wang, H. Zhang, C.-L. Li, J.M. Eisenschlos, V. Perot, Z. Wang, L. Miculicich, Y. Fujii, J. Shang, C.-Y. Lee, T. Pfister, Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.datak.2026.102596_b89","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"11006","article-title":"Chain-of-Thought reasoning in tabular language models","author":"Zheng","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b90","series-title":"Table-GPT: Table-tuned GPT for diverse table tasks","author":"Li","year":"2023"},{"key":"10.1016\/j.datak.2026.102596_b91","article-title":"Large language models (LLMs) on tabular data: Prediction, generation, and understanding - a survey","author":"Fang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.datak.2026.102596_b92","series-title":"Proceedings of the Extended Semantic Web Conference","article-title":"MammoTab 25: A large-scale dataset for semantic table interpretation \u2013 training, testing, and detecting weaknesses","author":"Cremaschi","year":"2025"},{"key":"10.1016\/j.datak.2026.102596_b93","series-title":"The Semantic Web \u2013 ISWC 2017: 16th International Semantic Web Conference, Vienna, Austria, October 21\u201325, 2017, Proceedings, Part I","first-page":"260","article-title":"Matching web tables with knowledge base entities: From entity lookups to entity embeddings","author":"Efthymiou","year":"2017"},{"key":"10.1016\/j.datak.2026.102596_b94","series-title":"SemTab@ ISWC","first-page":"13","article-title":"BiodivTab: A table annotation benchmark based on biodiversity research data.","author":"Abdelmageed","year":"2021"},{"key":"10.1016\/j.datak.2026.102596_b95","series-title":"The Semantic Web \u2013 ISWC 2020","first-page":"328","article-title":"Tough tables: Carefully evaluating entity linking for tabular data","author":"Cutrona","year":"2020"},{"key":"10.1016\/j.datak.2026.102596_b96","series-title":"Semantic Web Challenge on Tabular Data to Knowledge Graph Matching","article-title":"Results of semtab 2022","volume":"Vol. 3320","author":"Abdelmageed","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b97","series-title":"17th ISWC Workshop on Ontology Matching","first-page":"Online","article-title":"LamAPI: a comprehensive tool for string-based entity retrieval with type-base filters","author":"Avogadro","year":"2022"},{"key":"10.1016\/j.datak.2026.102596_b98","series-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2018"},{"key":"10.1016\/j.datak.2026.102596_b99","series-title":"Simple and scalable strategies to continually pre-train large language models","author":"Ibrahim","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b100","unstructured":"E.J. Hu, yelong shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, W. Chen, LoRA: Low-Rank Adaptation of Large Language Models, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.datak.2026.102596_b101","series-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2015"},{"key":"10.1016\/j.datak.2026.102596_b102","series-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"10.1016\/j.datak.2026.102596_b103","doi-asserted-by":"crossref","DOI":"10.1145\/3769120","article-title":"Sustainable quality in data preparation","author":"Pernici","year":"2025","journal-title":"ACM J. Data Inf. Qual."},{"key":"10.1016\/j.datak.2026.102596_b104","unstructured":"C.A. Bono, F. Belotti, M. Palmonari, Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data, in: Proceedings of the 20th International Workshop on Ontology Matching (OM 2025), Co-Located with ISWC 2025, Nara, Japan, 2025."}],"container-title":["Data & Knowledge Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X26000431?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0169023X26000431?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:47:21Z","timestamp":1776113241000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0169023X26000431"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":104,"alternative-id":["S0169023X26000431"],"URL":"https:\/\/doi.org\/10.1016\/j.datak.2026.102596","relation":{},"ISSN":["0169-023X"],"issn-type":[{"value":"0169-023X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"How good are LLMs in disambiguating entities in tabular data? A comprehensive study","name":"articletitle","label":"Article Title"},{"value":"Data & Knowledge Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.datak.2026.102596","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102596"}}