At this stage of the process, the ontology
entities are treated as ordinary words and can
consequently be part of many different domains
(e.g., 'Jaguar' can both be an animal and a car
brand). Clustering is done with the purpose of
indicating different domains. The result of this step
is a set of clusters for each entity. In addition, for
each cluster a cluster feature vector (CLFV) is
associated that is a product of all the DFVs of a
cluster.