Uncovering Hidden Trajectories: AI-Assisted Provenance Research of Post-WWII Acquisitions at the National Museum in Poznań

The National Museum in Poznań (Poland) Gallery of European Art houses numerous objects acquired post-1945 whose exact origins and wartime trajectories remain obscured. This paper analyzes the integration of Artificial Intelligence (AI) and digital humanities into the research workflows of the MNP. By utilizing Natural Language Processing (NLP) to extract data from unindexed texts and multilingual archives, we structure this information to create a database. This data is then analyzed using AI computational techniques, allowing us to uncover hidden patterns, identify key actors in the art market, and reconstruct the severed ownership chains of these post-war acquisitions. Through specific case studies from the Gallery, this contribution illustrates how new technological frameworks impact the daily practice of provenance research.