{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600551,"version":"4.3.3"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"Virtual Immersion in Territorial Arts"},{"name":"POR MARCHE FESR","award":["2014\/2020 8OS"],"award-info":[{"award-number":["2014\/2020 8OS"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Cult. Herit."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Virtual museums are factual means for the dissemination and documentation of Cultural Heritage (CH) content. They are suitable environments for the semantic annotation of artifacts and automatic virtual guides. To this end, we identify and compare Traditional (ontology-based), Large Language Model (LLM)-extended, and LLM-pure methods for the semantic information strategies of digital CH. The traditional method is described through an application prototype, while the methods that involve LLM are tested experimentally. To investigate the integral tasks related to LLMs, our experiments include (i) semantic annotation using the CIDOC Conceptual Reference Model (CRM) and Knowledge Graph (KG) generation with LLMs for a painting sample, and (ii) painting ranking relying solely on LLMs using catalog descriptions as input. The experiments demonstrate the potential of these methods to enhance artwork interpretation, description, and refinement of the results. Based on the relevant literature on traditional semantic annotation and conducted experiments with LLMs, a combination of ontologies and LLMs may provide an optimal approach, as it offers the accuracy of structured knowledge while providing a tool that interprets these elements into natural language and vice versa. Relying solely on LLMs may be risky due to the lack of domain-specific knowledge in the training data of LLMs, whereas traditional methods demand expertise in a specific domain and are more time-consuming. Our approach shows potential in use cases such as guiding museum visitors to artifacts that match their interests, assisting museum curators with documentation, or helping CH researchers identify similarities in artifact collections.<\/jats:p>","DOI":"10.1145\/3756016","type":"journal-article","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T15:38:47Z","timestamp":1753803527000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Knowledge Graphs vs. Large Language Models: Competitors or Partners in Supporting Virtual Museums"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4081-0203","authenticated-orcid":false,"given":"Iva","family":"Vasic","sequence":"first","affiliation":[{"name":"Department of Construction, Civil Engineering and Architecture, Marche Polytechnic University, Ancona, Italy  and Department of Informatics, University of Fribourg, Fribourg, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5076-5341","authenticated-orcid":false,"given":"Hans-Georg","family":"Fill","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Fribourg, Fribourg, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5637-6582","authenticated-orcid":false,"given":"Ramona","family":"Quattrini","sequence":"additional","affiliation":[{"name":"Department of Construction, Civil Engineering and Architecture, Marche Polytechnic University, Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9160-834X","authenticated-orcid":false,"given":"Roberto","family":"Pierdicca","sequence":"additional","affiliation":[{"name":"Department of Construction, Civil Engineering and Architecture, Marche Polytechnic University, Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58965-7_7"},{"key":"e_1_3_4_3_2","volume-title":"Proceedings of the 5th PAGES Open Science Meeting","author":"Arnaud Fabien","year":"2017","unstructured":"Fabien Arnaud, C\u00e9cile Pignol, Pierre St\u00e9phan, Anne-Lise Develle, P. Sabatier, Olivier Evrard, Brice Mourier, Maxime Debret, C\u00e9cile Grobois, Laurent Millet, et al. 2017. From core referencing to data re-use: Two French national initiatives to reinforce paleodata stewardship (National Cyber Core Repository and LTER France Retro-Observatory). In Proceedings of the 5th PAGES Open Science Meeting. HAL. Retrieved from https:\/\/hal.archives-ouvertes.fr\/hal-01616109"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47240-4_22"},{"key":"e_1_3_4_5_2","volume-title":"Digital Basic Cataloguing: 10 Principles","author":"Bergmeyer Winfried","year":"2022","unstructured":"Winfried Bergmeyer, Paul Klimpel, Anna Benedek, Ismo Malinen, Mareen Maa\u00df, Ariadna Matas, Liv Ramskjaer, and Sylvia Willkomm. 2022. Digital Basic Cataloguing: 10 Principles (1st ed.). Network of European Museum Organisations and German Museums Association.","edition":"1"},{"key":"e_1_3_4_6_2","first-page":"1877","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Proceedings of the Advances in Neural Information Processing Systems. H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33, Curran Associates, Inc., 1877\u20131901. Retrieved January 23, 2025 from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_4_7_2","unstructured":"Santiago Castro. 2017. Fast Krippendorff: Fast Computation of Krippendorff\u2019s Alpha Agreement Measure. Retrieved from https:\/\/github.com\/pln-fing-udelar\/fast-krippendorff"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIMSA.2009.5069914"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386454"},{"key":"e_1_3_4_10_2","unstructured":"Naem Chowdhury Abdoulsalam Awais Osman and Sheuly Aktar. 2023. Improving Customer Care with ChatGPT: A Case Study. Retrieved January 23 2025 from https:\/\/zenodo.org\/records\/7699658"},{"issue":"2","key":"e_1_3_4_11_2","first-page":"38","article-title":"Trasformazione digitale delle Collezioni civiche di Ascoli Piceno: Un progetto innovativo tra universit\u00e0 e musei","volume":"15","author":"Clini Paolo","year":"2024","unstructured":"Paolo Clini, Iva Vasic, Ramona Quattrini, Roberto Pierdicca, Eva S Malinverni, Stefano Papetti, and Matteo Felicetti. 2024. Trasformazione digitale delle Collezioni civiche di Ascoli Piceno: Un progetto innovativo tra universit\u00e0 e musei. Archeomatica 15, 2 (2024), 38\u201347.","journal-title":"Archeomatica"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0307472200003436"},{"key":"e_1_3_4_13_2","unstructured":"CIDOC CRM. 2021. CIDOC CRM RDF Data. Retrieved December 11 2023 from https:\/\/cidoc-crm.org\/rdfs\/7.1.2\/CIDOC_CRM_v7.1.2.rdf"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/1785162.1785216"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1017\/alj.2019.32"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3542700.3542709"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","unstructured":"Martin Doerr. 2009. Ontologies for cultural heritage. In Handbook on Ontologies. Steffen Staab and Rudi Studer (Eds.) Springer Berlin 463\u2013486. DOI: 10.1007\/978-3-540-92673-3_21","DOI":"10.1007\/978-3-540-92673-3_21"},{"key":"e_1_3_4_19_2","unstructured":"Martin Doerr Richard Light and Gerald Hiebel. 2020. Implementing the CIDOC Conceptual Reference Model in RDF. Retrieved July 18 2025 from https:\/\/cidoc-crm.org\/sites\/default\/files\/issue%20443%20-%20Implementing%20CIDOC%20CRM%20in%20RDF%20v1.1.pdf"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvlc.2018.06.005"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/DigitalHeritage.2018.8810001"},{"key":"e_1_3_4_22_2","first-page":"56","volume-title":"Companion Proceedings of the 43rd International Conference on Conceptual Modeling: ER Forum, Special Topics, Posters and Demos Co-located with ER 2024","author":"Fill Hans-Georg","year":"2024","unstructured":"Hans-Georg Fill, Felix H\u00e4rer, Iva Vasic, Daniel Borcard, Benedikt Reitemeyer, Fabian Muff, Simon Curty, and Marcel B\u00fchlmann. 2024. CMAG: A framework for conceptual model augmented generative artificial intelligence. In Companion Proceedings of the 43rd International Conference on Conceptual Modeling: ER Forum, Special Topics, Posters and Demos Co-located with ER 2024. Enrico Gallinucci, Hasan Yasar, Sotirios Liaskos, Patrick Marcel, Peter P. Chen, Sergio de Cesare, and Frederik Gailly (Eds.), CEUR Workshop Proceedings, Vol. 3849, CEUR-WS.org, 56\u201369. Retrieved from https:\/\/ceur-ws.org\/Vol-3849\/forum5.pdf"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","unstructured":"Hans-Georg Fill Peter Fettke and Julius K\u00f6pke. 2023. Conceptual modeling and large language models: Impressions from first experiments with ChatGPT. Enterprise Modelling and Information Systems Architectures 18 3 (2023) 1\u201315. DOI: 10.18417\/emisa.18.3","DOI":"10.18417\/emisa.18.3"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.3233\/SW-160240"},{"key":"e_1_3_4_25_2","unstructured":"Getty Research Institute. 2023. Getty Vocabularies: AAT ULAN TGN. Retrieved January 9 2024 from https:\/\/www.getty.edu\/research\/tools\/vocabularies\/index.html"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1006\/ijhc.1995.1081"},{"key":"e_1_3_4_27_2","unstructured":"Michael Gr\u00fcninger and Mark Fox. 1995. Methodology for the design and evaluation of ontologies. In The 1995 International Joint Conference on AI Montreal Quebec Canada. Retrieved from https:\/\/www.ijcai.org\/past\/ijcai-95\/"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.2200\/S01125ED1V01Y202109DSK022"},{"key":"e_1_3_4_29_2","volume-title":"International Standard Archival Description (General)","author":"International Council on Archives (ICA)","year":"2000","unstructured":"International Council on Archives (ICA). 2000. International Standard Archival Description (General) (2nd ed.). Retrieved January 9, 2024 from https:\/\/www.ica.org\/en\/isadg-general-international-standard-archival-description-second-edition","edition":"2"},{"key":"e_1_3_4_30_2","unstructured":"Dawn Kanter. 2024. Harnessing AI to Classify Early Modern Bible Illustrations. Features Research by Drew Thomas as Part of the Ornamento Project. Retrieved January 22 2025 from https:\/\/research.reading.ac.uk\/digitalhumanities\/harnessing-ai-to-classify-early-modern-bible-illustrations\/#_ftn2"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13772-3_38"},{"issue":"3","key":"e_1_3_4_32_2","first-page":"411","article-title":"Reliability in content analysis: Some common misconceptions and recommendations","volume":"30","author":"Krippendorff Klaus","year":"2004","unstructured":"Klaus Krippendorff. 2004. Reliability in content analysis: Some common misconceptions and recommendations. Human Communication Research 30, 3 (2004), 411\u2013433.","journal-title":"Human Communication Research"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3347317.3357245"},{"key":"e_1_3_4_34_2","first-page":"31","volume-title":"Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!","author":"Lewis Ashley","year":"2023","unstructured":"Ashley Lewis and Michael White. 2023. Mitigating harms of LLMs via knowledge distillation for a virtual museum tour guide. In Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants! Devamanyu Hazarika, Xiangru Robert Tang, and Di Jin (Eds.), Association for Computational Linguistics, Kerrville, TX, 31\u201345. Retrieved from https:\/\/aclanthology.org\/2023.tllm-1.4\/"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.3389\/feduc.2024.1328769"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW51313.2020.00133"},{"key":"e_1_3_4_37_2","first-page":"53","volume-title":"Proceedings of Text2Story\u20142nd Workshop on Narrative Extraction From Texts, co-located with the 41st European Conference on Information Retrieval (Text2Story@ECIR \u201919)","author":"Metilli Daniele","year":"2019","unstructured":"Daniele Metilli, Valentina Bartalesi, and Carlo Meghini. 2019. Steps towards a system to extract formal narratives from text. In Proceedings of Text2Story\u20142nd Workshop on Narrative Extraction From Texts, co-located with the 41st European Conference on Information Retrieval (Text2Story@ECIR \u201919). Al\u00edpio M\u00e1rio Jorge, Ricardo Campos, Adam Jatowt, and Sumit Bhatia (Eds.), CEUR Workshop Proceedings, Vol. 2342, CEUR-WS.org, 53\u201361. Retrieved from https:\/\/ceur-ws.org\/Vol-2342\/paper7.pdf"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/11891451_14"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.3233\/AO-230072"},{"key":"e_1_3_4_40_2","unstructured":"OpenAI. 2023. ChatGPT. Retrieved January 23 2023 from https:\/\/chat.openai.com\/"},{"key":"e_1_3_4_41_2","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. OpenAI Research. Retrieved January 23 2025 from https:\/\/openai.com\/research\/gpt-4v-system-card"},{"key":"e_1_3_4_42_2","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman et al. 2024. GPT-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_4_43_2","unstructured":"Jeff Z. Pan Simon Razniewski Jan-Christoph Kalo Sneha Singhania Jiaoyan Chen Stefan Dietze Hajira Jabeen Janna Omeliyanenko Wen Zhang Matteo Lissandrini et al. 2023. Large language models and knowledge graphs: Opportunities and challenges. arXiv:2308.06374. Retrieved from https:\/\/arxiv.org\/abs\/2308.06374"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6170-8_124"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.2423\/I22394303V11N1P151"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-60626-7_8"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3475720.3484445"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2008.08.001"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/5254.940028"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3114968"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457391"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71710-9_18"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.16212425"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656346"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003131816-6"},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/985040.985060"},{"key":"e_1_3_4_58_2","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00162"},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/2532630.2532634"}],"container-title":["Journal on Computing and Cultural Heritage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T21:07:57Z","timestamp":1782767277000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3756016"],"URL":"https:\/\/doi.org\/10.1145\/3756016","relation":{},"ISSN":["1556-4673","1556-4711"],"issn-type":[{"value":"1556-4673","type":"print"},{"value":"1556-4711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]},"assertion":[{"value":"2024-05-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}