From Show Programmes to Data: Designing a Workflow to Make Performing Arts Ephemera Accessible Through Language Models

TL;DR

This paper develops a workflow combining multimodal LLMs, ontology reasoning, and linked data frameworks to convert theatre programmes into structured, interoperable data, enhancing accessibility and analysis of performing arts collections.

Contribution

It introduces a novel integrated approach using vision-language models and ontology reasoning to automate the extraction and semantic annotation of theatre programmes.

Findings

Achieved over 98% accuracy in transcribing programmes

Demonstrated scalable ontology-driven analysis of performing arts data

Enabled alignment with existing knowledge graphs for interoperability

Abstract

Many heritage institutions hold extensive collections of theatre programmes, which remain largely underused due to their complex layouts and lack of structured metadata. In this paper, we present a workflow for transforming such documents into structured data using a combination of multimodal large language models (LLMs), an ontology-based reasoning model, and a custom extension of the Linked Art framework. We show how vision-language models can accurately parse and transcribe born-digital and digitised programmes, achieving over 98% of correct extraction. To overcome the challenges of semantic annotation, we train a reasoning model (POntAvignon) using reinforcement learning with both formal and semantic rewards. This approach enables automated RDF triple generation and supports alignment with existing knowledge graphs. Through a case study based on the Festival d'Avignon corpus, we demonstrate the potential for large-scale, ontology-driven analysis of performing arts data. Our results open new possibilities for interoperable, explainable, and sustainable computational theatre historiography.