Automatic annotation and modelling of works in eighteenth-century (music) theatre

Two members of the FWF GuDiE project team, Diana Korol and Jakob Leitner, led by PD Dr. Ingeborg Zechner, will speak on Friday, 27 February, at the conference "DHd 2026 – Not just text, not just data" in Vienna. The annual conference of the association "Digital Humanities in German-speaking Countries", organised by the University of Vienna, aims to create a productive space for encounters and discussions to address these questions. Panels, roundtable discussions, workshops and poster sessions bring together experts from the fields of digital cultural heritage research, digital archiving and data science, as well as representatives of traditional, text- and language-oriented digital humanities. In recent years,

numerous humanities disciplines have significantly expanded the basis of their research work through the digital recording of cultural products and abstract modelling of information. The starting point for this was primarily the creation of text corpora and the development of algorithms and interfaces for text analysis. Gradually, the field has expanded, so that now it is possible to digitally capture and increasingly link together all "objects" in the humanities: people, places, objects of material culture, concepts, works of art, linguistic interactions, etc. Challenges arising from this expansion beyond text and data are taken up as the motto of the conference: not by excluding text-centred approaches, but by placing them in a broader context.

Further information on the conference and the programme

The contribution by Diana Korol and Jakob Leitner presents a hybrid approach to annotating and modeling references to theatrical works in eighteenth-century theatre chronicles. As part of the FWF-funded project GuDiE (2024–2028), a digital critical edition of the Gumpenhuber chronicles is being developed using TEI/XML, alongside an RDF database based on performing arts ontologies. Due to the fluid and hybrid nature of historical theatre practices—such as pasticcio or cross-genre adaptations—works are modeled not as abstract entities but as expressions enriched with content types (e.g., music, text, choreography). To support the annotation process, Large Language Models (LLMs) were used for semi-automatic Named Entity Recognition and linking to a curated authority register. Results show that LLMs can reduce manual effort, though challenges such as ambiguity, disambiguation, and prompt sensitivity remain. This contribution reflects on the methodological and ontological implications of combining structured data modeling with historical complexity in digital scholarly editing.