In this paper, we describe an ontology-driven pattern disambiguation process for Rote Extractors. Our approach can generate lexical patterns for a particular relation from unrestricted text. Then patterns can be used to recognize concepts, which have the same relation in other text. We test our experiments with/without the ontology. The results show that our approach can dramatically improve the performance of existing pattern-based Rote Extractors. Keywords Edit-Distance, Lexical Pattern, OWL, Ontology Query, Pattern disambiguation, Pattern Generalization, POS tagging, NER and Semantic Web.