{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:26:30Z","timestamp":1777937190799,"version":"3.51.4"},"reference-count":69,"publisher":"Emerald","issue":"7","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":5,"URL":"https:\/\/creativecommons.org\/licences\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,12,14]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Cultural heritage (CH) texts contain rich knowledge that is difficult to query systematically due to the challenges of converting unstructured discourse into structured knowledge graphs (KGs). This paper introduces ATR4CH (Adaptive Text-to-RDF for Cultural Heritage), a systematic five-step methodology for Large Language Model (LLM)-based knowledge extraction from CH documents. We validate the methodology through a case study on authenticity assessment debates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design\/methodology\/approach<\/jats:title>\n                    <jats:p>ATR4CH combines annotation models, ontological frameworks and LLM-based extraction through iterative development: foundational analysis, annotation schema development, pipeline architecture, integration refinement and comprehensive evaluation. We demonstrate the approach using Wikipedia articles about disputed items (documents, artifacts, etc.), implementing a sequential pipeline with three LLMs (Claude Sonnet 3.7, Llama 3.3 70B and GPT-4o-mini).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>The methodology successfully extracts complex CH knowledge: 0.96\u20130.99 F1 for metadata extraction, 0.7\u20130.8 F1 for entity recognition, 0.65\u20130.75 F1 for hypothesis extraction, 0.95\u20130.97 for evidence extraction and 0.62 G-EVAL for discourse representation. Smaller models performed competitively, enabling cost-effective deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Research limitations\/implications<\/jats:title>\n                    <jats:p>The produced KG is limited to Wikipedia articles. While the results are encouraging, human oversight is necessary during post-processing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Originality\/value<\/jats:title>\n                    <jats:p>To the best of the authors\u2019 knowledge, this is the first systematic methodology for coordinating LLM-based extraction with CH ontologies. ATR4CH provides a replicable framework adaptable across CH domains and institutional resources. ATR4CH enables CH institutions to systematically convert textual knowledge into queryable KGs, supporting automated metadata enrichment and knowledge discovery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1108\/jd-07-2025-0203","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T04:31:39Z","timestamp":1774413099000},"page":"206-250","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge graphs generation from cultural heritage texts: combining LLMs and ontological engineering for scholarly debates"],"prefix":"10.1108","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7865-7537","authenticated-orcid":true,"given":"Andrea","family":"Schimmenti","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Bologna , ,","place":["Bologna, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5931-5187","authenticated-orcid":true,"given":"Valentina","family":"Pasqual","sequence":"additional","affiliation":[{"name":"Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Center (\/DH.arc), University of Bologna , ,","place":["Bologna, Italy"]}]},{"given":"Fabio","family":"Vitali","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Bologna , ,","place":["Bologna, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9195-8203","authenticated-orcid":true,"given":"Marieke","family":"van Erp","sequence":"additional","affiliation":[{"name":"DHLab, KNAW Humanities Cluster , ,","place":["Amsterdam, Netherlands"]}]}],"member":"140","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"issue":"1","key":"2026050123525596800_ref001","doi-asserted-by":"publisher","first-page":"3:1","DOI":"10.4230\/TGDK.1.1.3","article-title":"Knowledge engineering using Large Language Models","volume":"1","author":"Allen","year":"2023","journal-title":"Transactions on Graph Data and Knowledge"},{"key":"2026050123525596800_ref002","article-title":"Musical Meetups: a knowledge graph approach for historical social network analysis","author":"Alba Morales","year":"2023"},{"key":"2026050123525596800_ref003","volume-title":"GrapHNR 2023","author":"Andrews","year":"2023"},{"issue":"1","key":"2026050123525596800_ref005","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3555312","article-title":"Knowledge graph construction with a fa\u00e7ade: a unified method to access heterogeneous data sources on the web","volume":"23","author":"Asprino","year":"2023","journal-title":"ACM Transactions on Internet Technology"},{"key":"2026050123525596800_ref006","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"2026050123525596800_ref007","first-page":"104","article-title":"Supporting complexity and conjectures in cultural heritage descriptions","author":"Barabucci","year":"2021"},{"issue":"7","key":"2026050123525596800_ref008","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1108\/JD-09-2022-0207","article-title":"Is dc:subject enough? A landscape on iconography and iconology statements of knowledge graphs in the semantic web","volume":"79","author":"Baroncini","year":"2023","journal-title":"Journal of Documentation"},{"key":"2026050123525596800_ref009","volume-title":"Atti Dell'Accademia Pontaniana","author":"Barone","year":"1912"},{"key":"2026050123525596800_ref010","doi-asserted-by":"publisher","first-page":"22539","DOI":"10.18653\/v1\/2025","volume-title":"Findings of the Association for Computational Linguistics: ACL 2025","author":"Ben Abacha","year":"2025"},{"key":"2026050123525596800_ref011","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14923857","article-title":"New frontiers in digital libraries: the trajectory of digital humanities through a computational lens","author":"Bernasconi","year":"2024"},{"issue":"5","key":"2026050123525596800_ref012","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/scientificamerican0501-34","article-title":"The semantic web","volume":"284","author":"Berners-Lee","year":"2001","journal-title":"Scientific American"},{"issue":"3","key":"2026050123525596800_ref013","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1111\/j.1468-2303.2011.00590.x","article-title":"Uncertainty and the history of ideas","volume":"50","author":"Blau","year":"2011","journal-title":"History and Theory"},{"key":"2026050123525596800_ref014","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"issue":"2","key":"2026050123525596800_ref071","first-page":"249","article-title":"Assessing agreement on classification tasks: the kappa statistic","volume":"22","author":"Carletta","year":"1996","journal-title":"Computational Linguistics"},{"key":"2026050123525596800_ref004","first-page":"221","volume-title":"ISWC (Satellites)","author":"Carriero","year":"2019"},{"issue":"4","key":"2026050123525596800_ref015","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.websem.2005.09.001","article-title":"Named graphs","volume":"3","author":"Carroll","year":"2005","journal-title":"Journal of Web Semantics"},{"issue":"1","key":"2026050123525596800_ref070","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educational and Psychological Measurement"},{"key":"2026050123525596800_ref016","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24129-6_37","volume-title":"Metadata and Semantics Research. MTSR 2015, Volume 544 of Communications in Computer and Information Science","author":"Daquino","year":"2015"},{"issue":"3","key":"2026050123525596800_ref017","doi-asserted-by":"publisher","first-page":"59","DOI":"10.4403\/jlis.it-12642","article-title":"Knowledge representation of digital hermeneutics of archival and literary sources","volume":"11","author":"Daquino","year":"2020","journal-title":"JLIS.it"},{"key":"2026050123525596800_ref072","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","volume-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)","author":"Devlin","year":"2019"},{"issue":"6","key":"2026050123525596800_ref018","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.3233\/SW-243686","article-title":"On assessing weaker logical status claims in Wikidata cultural heritage records","volume":"15","author":"Di Pasquale","year":"2024","journal-title":"Semantic Web: Interoperability, Usability, Applicability"},{"key":"2026050123525596800_ref019","article-title":"RML: a generic language for integrated RDF mappings of heterogeneous data","author":"Dimou","year":"2014"},{"issue":"3","key":"2026050123525596800_ref020","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1609\/aimag.v24i3.1720","article-title":"The cidoc conceptual reference module: an ontological approach to semantic interoperability of metadata","volume":"24","author":"Doerr","year":"2003","journal-title":"AI Magazine"},{"key":"2026050123525596800_ref021","unstructured":"Dubey, A., Jauhri, A. and Pandey, A. (2024), \u201cThe llama 3 herd of models\u201d, available at:\u00a0https:\/\/arxiv.org\/abs\/2407.21783."},{"key":"2026050123525596800_ref073","volume-title":"Truth and Method","author":"Gadamer","year":"2013"},{"key":"2026050123525596800_ref022","article-title":"An application of Text2AMR2FRED to the musical heritage domain","author":"Gangemi","year":"2024"},{"key":"2026050123525596800_ref023","doi-asserted-by":"publisher","first-page":"179","DOI":"10.18653\/v1\/P17-1017","article-title":"Creating training corpora for NLG micro-planners","author":"Gardent","year":"2017"},{"issue":"20","key":"2026050123525596800_ref024","doi-asserted-by":"publisher","first-page":"115","DOI":"10.6092\/issn.2532-8816\/21229","article-title":"Expliciting contexts: semantic knowledge extraction from traditional archival descriptions","volume":"9","author":"Giagnolini","year":"2025","journal-title":"Umanistica Digitale"},{"key":"2026050123525596800_ref025","doi-asserted-by":"publisher","first-page":"881","DOI":"10.12688\/f1000research.72843.2","article-title":"An empirical study on resource description framework reification for trustworthiness in knowledge graphs","volume":"10","author":"Govindapillai","year":"2021","journal-title":"F1000Research"},{"key":"2026050123525596800_ref026","first-page":"134","article-title":"Verzeichnis der den ober\u00f6sterreichischen raum betreffenden gef\u00e4lschten, manipulierten oder verd\u00e4chtigten mittelalterlichen urkunden","author":"Haider","year":"2022"},{"key":"2026050123525596800_ref027","first-page":"247","article-title":"Il falso documento del conte giovanni di moggio (875)","author":"H\u00e4rtel","year":"2017"},{"key":"2026050123525596800_ref028","article-title":"Foundations of rdf\u2217and sparql\u2217:(an alternative approach to statement-level metadata in rdf)","author":"Hartig","year":"2017"},{"key":"2026050123525596800_ref029","doi-asserted-by":"publisher","first-page":"10219","DOI":"10.18653\/v1\/2025","article-title":"Evaluating and improving graph to text generation with large language models","author":"He","year":"2025"},{"issue":"2","key":"2026050123525596800_ref030","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3233\/SW-180333","article-title":"Information extraction meets the Semantic Web: a survey","volume":"11","author":"Hotho","year":"2020","journal-title":"Semantic Web"},{"key":"2026050123525596800_ref031","article-title":"Definition of frbroo: a conceptual model for bibliographic information in object-oriented formalism","author":"IFLA Working Group on FRBR\/CRM Dialogue","year":"2017","journal-title":"Technical Report"},{"key":"2026050123525596800_ref033","unstructured":"Khorashadizadeh, H., Zahra Amara, F., Ezzabady, M., Ieng, F., Tiwari, S., Mihindukulasooriya, N., Groppe, J., Sahri, S., Benamara, F. and Groppe, S. (2024), \u201cResearch Trends for the Interplay between Large Language Models and knowledge graphs\u201d, available at:\u00a0http:\/\/arxiv.org\/abs\/2406.08223"},{"key":"2026050123525596800_ref032","first-page":"5","article-title":"The INCEpTION platform: machine-assisted and knowledge-oriented interactive annotation","author":"Klie","year":"2018"},{"key":"2026050123525596800_ref034","doi-asserted-by":"publisher","DOI":"10.4135\/9781071878781","volume-title":"Content Analysis: An Introduction to its Methodology","author":"Krippendorff","year":"2019","edition":"4th ed."},{"key":"2026050123525596800_ref035","doi-asserted-by":"crossref","unstructured":"Lairgi, Y., Moncla, L., Cazabet, R., Benabdeslem, K. and Cl\u00e9au, P. (2024), \u201ciText2KG: incremental knowledge graphs construction using Large Language Models\u201d, available at:\u00a0http:\/\/arxiv.org\/abs\/2409.03284","DOI":"10.1007\/978-981-96-0573-6_16"},{"key":"2026050123525596800_ref036","article-title":"Prov-o: the prov ontology. W3c recommendation","author":"Lebo","year":"2013","journal-title":"World Wide Web Consortium"},{"key":"2026050123525596800_ref037","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2020"},{"key":"2026050123525596800_ref038","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/978-3-031-06981-9_23","volume-title":"The Semantic Web","author":"Lisena","year":"2022"},{"key":"2026050123525596800_ref039","doi-asserted-by":"publisher","first-page":"2511","DOI":"10.18653\/v1\/2023.emnlp-main.153","article-title":"G-eval: NLG evaluation using gpt-4 with better human alignment","author":"Liu","year":"2023"},{"key":"2026050123525596800_ref040","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79474-2","volume-title":"Synthesis Lectures on Data, Semantics, and Knowledge","author":"Maynard","year":"2017"},{"key":"2026050123525596800_ref041","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70407-4_9","article-title":"Amr2fred, a tool for translating abstract meaning representation to motif-based linguistic knowledge graphs","author":"Meloni","year":"2017"},{"key":"2026050123525596800_ref042","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-658-43705-3_8","article-title":"Llm-assisted knowledge graph engineering: experiments with chatgpt","author":"Meyer","year":"2024"},{"key":"2026050123525596800_ref043","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47243-5_14","volume-title":"The Semantic Web \u2013 ISWC 2023, Volume 14266 of Lecture Notes in Computer Science","author":"Mihindukulasooriya","year":"2023"},{"key":"2026050123525596800_ref044","first-page":"11048","article-title":"Rethinking the role of demonstrations: what makes in-context learning work?","author":"Min","year":"2022"},{"key":"2026050123525596800_ref045","unstructured":"Ontotext\n           (2024), \u201cGraphdb: semantic database\u201d, available at:\u00a0https:\/\/www.ontotext.com\/products\/graphdb\/"},{"key":"2026050123525596800_ref046","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"2026050123525596800_ref047","article-title":"The critical inquiry in humanities knowledge graphs: challenges, methods","author":"Pasqual","year":"2025"},{"key":"2026050123525596800_ref048","doi-asserted-by":"publisher","first-page":"47","DOI":"10.4324\/9780080458397-10","volume-title":"Introducing Information Management: The Business Approach","author":"Peter","year":"2006"},{"key":"2026050123525596800_ref049","doi-asserted-by":"publisher","first-page":"2463","DOI":"10.18653\/v1\/D19-1250","article-title":"Language models as knowledge bases?","author":"Petroni","year":"2019"},{"key":"2026050123525596800_ref050","doi-asserted-by":"publisher","first-page":"10","DOI":"10.4119\/unibi\/2983506","volume-title":"Uncertainty as Unavoidable Good","author":"Piotrowski","year":"2023"},{"key":"2026050123525596800_ref051","article-title":"Prospects for computational hermeneutics","author":"Piotrowski","year":"2020"},{"key":"2026050123525596800_ref052","first-page":"392","article-title":"chrF: character n-gram F-score for automatic MT evaluation","author":"Popovi\u0107","year":"2015"},{"key":"2026050123525596800_ref053","first-page":"83","article-title":"Extreme design with content ontology design patterns","author":"Presutti","year":"2009"},{"issue":"4","key":"2026050123525596800_ref054","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704435","article-title":"Tool learning with foundation models","volume":"57","author":"Qin","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"2026050123525596800_ref055","doi-asserted-by":"publisher","first-page":"23411","DOI":"10.1609\/aaai.v38i21.30406","article-title":"Learning pattern-based extractors from natural language and knowledge graphs: applying Large Language Models to Wikipedia and linked open data","author":"Ringwald","year":"2024"},{"key":"2026050123525596800_ref056","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2024.1472512","article-title":"Combining language models for knowledge extraction from Italian TEI editions","volume":"6","author":"Santini","year":"2024","journal-title":"Frontiers of Computer Science"},{"issue":"3","key":"2026050123525596800_ref057","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/3594724","article-title":"An ontology for comprehensive artistic interpretations","volume":"16","author":"Sartini","year":"2023","journal-title":"Journal on Computing and Cultural Heritage"},{"key":"2026050123525596800_ref058","article-title":"Toolformer: language models can teach themselves to use tools","author":"Schick","year":"2023"},{"key":"2026050123525596800_ref059","doi-asserted-by":"publisher","first-page":"463","DOI":"10.6092\/unibo\/amsacta\/7927","article-title":"Structuring authenticity assessments on historical documents using llms","author":"Schimmenti","year":"2024"},{"key":"2026050123525596800_ref060","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3522586","article-title":"Defining a knowledge graph development process through a systematic review","volume":"32","author":"Tamasauskait\u0117","year":"2022","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"issue":"2","key":"2026050123525596800_ref061","doi-asserted-by":"publisher","first-page":"411","DOI":"10.2426\/aibstudi-12068","article-title":"Digital humanities e organizzazione della conoscenza: una pratica di insegnamento nel lodlam","volume":"60","author":"Tomasi","year":"2020","journal-title":"AIB STUDI"},{"key":"2026050123525596800_ref062","volume-title":"The Treatise of Lorenzo Valla on the Donation of Constantine","author":"Valla","year":"2023"},{"issue":"3","key":"2026050123525596800_ref063","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1177\/0165551509360123","article-title":"Ontology-based information extraction: an introduction and a survey of current approaches","volume":"36","author":"Wimalasuriya","year":"2010","journal-title":"Journal of Information Science"},{"key":"2026050123525596800_ref064","first-page":"27263","article-title":"BartScore: evaluating generated text as text generation","volume":"34","author":"Yuan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026050123525596800_ref065","doi-asserted-by":"publisher","first-page":"5364","DOI":"10.18653\/v1\/2024.naacl-long.300","article-title":"GLiNER: generalist model for named entity recognition using bidirectional transformer","author":"Zaratiana","year":"2024"}],"container-title":["Journal of Documentation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/jd\/article-pdf\/82\/7\/206\/11415201\/jd-07-2025-0203en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/jd\/article-pdf\/82\/7\/206\/11415201\/jd-07-2025-0203en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:53:05Z","timestamp":1777693985000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/jd\/article\/82\/7\/206\/1352307\/Knowledge-graphs-generation-from-cultural-heritage"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":69,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,12,14]]}},"URL":"https:\/\/doi.org\/10.1108\/jd-07-2025-0203","relation":{},"ISSN":["0022-0418","1758-7379"],"issn-type":[{"value":"0022-0418","type":"print"},{"value":"1758-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]}}}