Structured data extracted from the Web is highly heterogeneous due to its disparate origins and nature. There exist some techniques to integrate this information based on the extraction of synonymy relationships among the different entities involved. However, synonymy is a very strict and therefore uncommon relationship. We present a novel approach for the discovery of subsumption relationships among concepts from different ontologies. Our approach is based on the use of generic rules, designed to capture the existence of a subsumption relationship, considering features of the ontological context of concepts (i.e., labels, roles, and hierarchical relationships).