Laroche, FlorentVilain, AmbreVauxion, MathisChenadec, Elouarn LeCampana, StefanoFerdani, DanieleGraf, HolgerGuidi, GabrieleHegarty, ZackaryPescarin, SofiaRemondino, Fabio2025-09-052025-09-052025978-3-03868-277-6https://doi.org/10.2312/dh.20253170https://diglib.eg.org/handle/10.2312/dh20253170This article explores the intersection of artificial intelligence (AI), 3D modeling, and historical ontology in the context of digital heritage. It presents an interdisciplinary methodology designed to enhance the accuracy and epistemological transparency of virtual reconstructions, using the lost Cordeliers Church of Nantes as a case study. Generative AI models, supported by curated databases and structured ontologies (OMeKA-S), are used to produce historically grounded visual hypotheses. The process includes source verification, bias analysis, and an iterative evaluation protocol by domain experts. The study also examines the ethical and methodological implications of using AI in the humanities, advocating for transparent, explainable, and human-centered AI workflows. By combining technical innovation with heritage expertise, this work offers a reproducible framework for digital museography and future research in the digital humanities.Attribution 4.0 International LicenseCCS Concepts: Information systems → Information retrieval → Users and interactive retrieval Human-centered computing Computing methodologies → Artificial intelligenceInformation systems → Information retrieval → Users and interactive retrieval Humancentered computing Computing methodologies → Artificial intelligence10.2312/dh.202531708 pages