Erlangen-Prehistoric (FAU Erlangen) Collection

This dataset originates from the Collection for Prehistory and Protohistory at the Friedrich-Alexander Universität Erlangen-Nürnberg. We processed 308 pages of the historic “Inventarbuch der Anthropologisch Prähistorischen Sammlung”, which is publicly available through the collection’s digital archive (https://www.uf.phil.fau.de/abteilungen/sammlung/inventarbuecher/). Ground-truth transcriptions were generated using Gemini3 and subsequently manually verified. The documents are predominantly handwritten with printed headers or labels. The handwritten nature of most entries, combined with historical script variations and occasional degradation, makes this dataset particularly challenging for OCR systems.