Leveraging Large Language Models to Identify Event-Driven Changes in Wikidata Entities

Wikidata undergoes continuous updates from a diverse community of users. This paper explores the work in progress on the application of Large Language Models (LLMs) to establish connections between these entity modifications and real-world events sourced from open databases. By presenting the LLM with a customized prompt alongside relevant events linked to the entity, we instruct the model to identify the event most likely responsible for the observed change. This approach offers causal explanations for entity updates and enriches the contextual understanding of the factors driving changes within a collaboratively edited knowledge base. Ultimately, this research aims to contribute to a deeper understanding of the dynamics that shape the evolution of crowdsourced knowledge bases such as Wikidata.