From Show Programs to Linked Data
A Generative AI Workflow for Performing Arts Collections
DOI:
https://doi.org/10.5860/ital.v45i3.17708Keywords:
Large Language Model (LLM), OCR, Cultural Heritage, Performing arts, Ontology, Knowledge Graph, Linked Data, Semantic annotationAbstract
Many heritage institutions hold extensive collections of show programs. Too numerous to be cataloged individually, they remain difficult to access and are still largely undigitized. This paper presents a workflow for transforming such documents into structured, interoperable data by combining vision-language models (VLMs), a custom extension of the Linked Art ontology for the performing arts, and different approaches for automatic semantic data annotation. Using the Festival d’Avignon programs (1947–present), preserved at the Bibliothèque nationale de France, as a case study, we demonstrate how VLMs achieve more than 98% text transcription accuracy from heterogeneous heritage document images and how constraining large language model generation through a knowledge graph significantly reduces hallucinations in semantic annotation. We argue that this workflow opens new possibilities for large-scale, interoperable performing arts historiography, including the creation of catalogues raisonnés for performing artists, a form of scholarship common in visual arts but absent in performing arts studies.
References
Antonio Lieto et al., “Conceptual Models for Intangible Art: A Formal Modeling Proposal,” Mimesis Journal 3, no. 2 (2014): 2, https://doi.org/10.4000/mimesis.690.
Artsdata, “Artsdata Data Model v1.0,” last modified July 26, 2026, https://docs.artsdata.ca/.
Benjamin Kiessling and Thibault Clérice, “Does Context Matter? Enhancing Handwritten Text Recognition with Metadata in Historical Manuscripts,” CHR2024 – Computational Humanities Research Conference (Aarhus, Denmark), December 2024, https://inria.hal.science/hal-04704547.
Clarisse Bardiot, Performing Arts and Digital Humanities: From Traces to Data (London, UK: ISTE Ltd., 2021).
Darren Edge et al., “From Local to Global: A Graph RAG Approach to Query-Focused Summarization,” preprint, arXiv, February 19, 2025, https://doi.org/10.48550/arXiv.2404.16130; Bian, “LLM-Empowered Knowledge Graph Construction.”
Daya Guo et al., “DeepSeek-R1 Incentivizes Reasoning in LLMs through Reinforcement Learning,” Nature 645, no. 8081 (2025): 633–38, https://doi.org/10.1038/s41586-025-09422-z.
Eudes Peyre et al., “CapData opéra: faciliter l’interopérabilité des données des maisons d’opéra,” in 10e conférence nationale sur les applications pratiques de l’intelligence artificielle, edited by Catherine Roussey and Ghislain Atemezing (La Rochelle, France: Plate-Forme Intelligence Artificielle, 2024), https://hal.science/hal-04639095.
Gavin Greif et al., “Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents,” preprint, arXiv, April 1, 2025, https://doi.org/10.48550/arXiv.2504.00414.
George Bruseker et al., “The Semantic Reference Data Modelling Method: Creating Understandable, Reusable and Sustainable Semantic Data Models,” Journal of Open Humanities Data 11 (March 2025): 22. https://doi.org/10.5334/johd.282.
Haonan Bian, “LLM-Empowered Knowledge Graph Construction: A Survey,” preprint, arXiv, October 23, 2025, https://doi.org/10.48550/arXiv.2510.20345.
Iris Berbain and Cécile Obligi, “Preserving Theater Ephemera, from Programs to Websites,” trans. Saskia Brown, Hybrid. Revue des arts et médiations humaines, no. 1 (July 2014): 1, https://doi.org/10.4000/hybrid.1080.
Jonathan Bollen, “Data Models for Theatre Research: People, Places, and Performance,” Theatre Journal 68, no. 4 (2016): 615–32, https://doi.org/10.1353/tj.2016.0109.
Marine Roussillon and Christophe Schuwey, eds., Revue d’historiographie du théâtre: écrire l’histoire des spectacles avec des bases de données (Société d’histoire du théâtre, France, 2020), https://sht.asso.fr/revue/ecrire-lhistoire-des-spectacles-avec-des-bases-de-donnees/; Thunnis van Oort and Julia Noordegraaf, eds., Research Data Journal for the Humanities and Social Sciences. Special Issue: Structured Data for Performing Arts History 5, no. 2 (2020), https://brill.com/view/journals/rdj/5/2/rdj.5.issue-2.xml; Bardiot, Performing Arts and Digital Humanities; Marc Douguet, ed., Revue d’historiographie du théâtre: La base CESAR, bilan et perspectives (Société d’histoire du théâtre, France, 2024), https://sht.asso.fr/numero/la-base-cesar-bilan-et-perspectives/.
Matteo Romanello et al., “Predicting the Fictional Time and Space of French Theatre Plays by Using Large Language Models,” IEEE International Conference on Cyber Humanities (Florence, Italy: IEEE, September 2025), https://hal.science/hal-05157140.
Maud Ehrmann et al., “Named Entity Recognition and Classification in Historical Documents: A Survey,” ACM Computing Surveys 56, no. 2 (2023): 1–47, https://doi.org/10.1145/3604931; Solenn Tual et al., “A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documents,” preprint, arXiv, February 20, 2023, https://doi.org/10.48550/arXiv.2302.10204.
Pascal Hitzler et al., “Neural-Symbolic Integration and the Semantic Web,” Semantic Web 11, no. 1 (2020): 3–11, https://doi.org/10.3233/sw-190368.
Qianyu Meng et al., “Agent Harness for Large Language Model Agents: A Survey,” preprint, Preprints.org, April 7, 2026, https://doi.org/10.20944/preprints202604.0428.v1.
Seorin Kim et al., “Early Evidence of How LLMs Outperform Traditional Systems on OCR/HTR Tasks for Historical Records,” preprint, arXiv, 2025, https://doi.org/10.48550/ARXIV.2501.11623.
Swiss Performing Arts Shapes, “Swiss Performing Arts Data Model Documentation,” https://shapes.performing-arts.ch/.
Yupan Huang et al., “LayoutLMv3: Pre-Training for Document AI with Unified Text and Image Masking,” preprint, arXiv, July 19, 2022, https://doi.org/10.48550/arXiv.2204.08387; Minghao Li et al., “TrOCR: Transformer-Based Optical Character Recognition with Pre-Trained Models,” preprint, arXiv, September 6, 2022, https://doi.org/10.48550/arXiv.2109.10282.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Clarisse Bardiot, Bernard Jacquemin, Jacob Hart, George Bruseker, Antonios Lagarias, Pierre-Carl Langlais, Brandon Farnsworth, Jeanne Fras
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors that submit to Information Technology and Libraries agree to the Copyright Notice.
