As part of the Cognisearch project, we developed a general architecture dedicated to extracting, indexing and searching for complex Named Entities (NEs) in webpages. We consider complex NEs as NEs represented by a list of properties that can be single values (text, number, etc.), "elementary" NEs and/or other complex NEs. Before the indexing of a new extracted complex NE, it is important to make sure that it is not already indexed. Indeed, the same NE may be referenced on several different web platforms. Therefore, we need to be able to establish similarity to consolidate information related to similar complex NEs. This is the focus of this paper. Two issues mainly arise in the computation of similarity between complex NEs: (i) the same property may be expressed differently in the compared NEs; (ii) some properties may be missing. We propose several generic similarity computation approaches that target any type of complex NEs. The two issues outlined above are tackled in these proposals. We experiment and evaluate these approaches with two examples of complex NEs related to the domain of social events.