In this paper we propose an NLP-based method for Ontology Population from texts and apply it to semi automatic instantiate a Generic Knowledge Base (Generic Domain Ontology) in the risk management domain. The approach is semi-automatic and uses a domain expert intervention for validation. The proposed approach relies on a set of Instances Recognition Rules based on syntactic structures, and on the predicative power of verbs in the instantiation process. It is not domain dependent since it heavily relies on linguistic knowledge. A description of an experiment performed on a part of the ontology of the PRIMA project (supported by the European community) is given. A first validation of the method is done by populating this ontology with Chemical Fact Sheets from Environmental Protection Agency . The results of this experiment complete the paper and support the hypothesis that relying on the predicative power of verbs in the instantiation process improves the performance.