In this step, a search query is prepared for each
entity while the actual search is performed in Step
4. The query is based on the entity name and
optionally expanded with selected neighbouring
entities and/or keywords. The motivation behind
expanding the initial query with neighbouring
entities is to create a query that reflects both the
ontology and the relationship of each entity to
other neighbouring entities. The question at this
stage is, what kind of neighbouring entities is
optimal to include? Do keywords provide better
FVs?