Generating complex ontology instances from documents

This paper presents a novel Information Extraction system able to generate complex instances from free text available on the Web. The approach is based on a non-monotonical processing over ontologies, and makes use of entity recognizers and disambiguators in order to adequately extract and combine instances and their relations. Experiments conducted over the archaeology research domain provide encouraging results in both efficiency and efficacy and suggest that the tool is suitable for its application on other similar Semantic Web resources.