Entity mining is still a troublesome open problem. In past years many approaches allowed to automate the generation of equivalence links between references using schema matching or various heuristics based on the recognition of similar property values. In contrast, few of them considered the analysis of the network of equivalence links (“equivalence network”) as an indication of the likelihood and strength of the equivalence. Following this basic idea, in this paper we apply the well known Girvan and Newman algorithm to partition existing equivalence networks into clusters of co-references and gain an insight of their nature, size and composition.