Social networks have recently garnered considerable interest. With the intention of utilizing social networks for the SemanticWeb, several studies have examined automatic extraction of social networks. However, most methods have addressed extracting the strength of relations. Our goal is extracting underlying relations between entities embedded in social networks. To this end, we propose a method that automatically extracts labels that describe relations between entities. The fundamental idea is to cluster similar entity pairs according to their collective contexts in Web documents. The descriptive labels for relations are obtained from results of clustering. The proposed method is entirely unsupervised and is easily incorporated with existing social network extraction methods. Our method also contributes to ontology population by find relations between intances in social network. Our experiments conducted on entities in political social networks achieved clustering with high precision and recall. We were able to extract appropriate relation labels to represent the entities.