This is a domain-independent system that extracts information from unstructured texts and populates a database.
It has four modes: Who is Who?, Contact Info, Synopsis and Batch Summarizer. The program identifies entities such as persons, organizations, locations, and other types of data as well as relationships between entities.
It processes text files in the HTML, PDF, DOC, RTF and ASCII formats. The program can start with processing local sources or first retrieving relevant materials from the WWW.