KIEV: a Tool for Extracting Semantic Relations from the World Wide Web

Deriving knowledge from information stored in unstructured documents is a major challenge. The proliferation of knowledge sharing communities such as Wikipedia urge for automatic methods to construct a knowledge base consisting of entities and their relationships for advanced querying. More specifically, binary relationships representing a fact between two entities can be extracted to populate semantic triple stores or large knowledge bases. In this paper, we present our novel tool KIEV to fulfil this task. It combines a discovery process and a verification process for the entities and the type of relationship. We finally demonstrate three use cases for which KIEV is useful.