This paper presents the process of annotating and modelling a corpus to automatically detect named entities in medieval charters in French. It introduces a new annotated corpus and a new system which outperforms state-of-the art libraries. Charters are legal documents and among the most important historical sources for medieval studies as they reflect economic and social dynamics as well as the evolution of literacy and writing practices. Automatic detection of named entities greatly improves the access to these unstructured texts and facilitates historical research. The experiments described here are based on a corpus encompassing about 500k words (1200 charters) coming from three charter collections of the 13th and 14th centuries. We annotated the corpus and then trained two state-of-the art NLP libraries for Named Entity Recognition (Spacy and Flair) and a custom neural model (Bi-LSTM-CRF). The evaluation shows that all three models achieve a high performance rate on the test set and a high generalization capacity against two external corpora unseen during training. This paper describes the corpus and the annotation model, and discusses the issues related to the linguistic processing of medieval French and formulaic discourse, so as to interpret the results within a larger historical perspective.