Hugo Zaragoza describes it on the What is Correlator page,
The core of Correlator is a search engine capable of returning not only relevant documents, but also relevant sentences and entities. This search engine is the fruit of work at the Yahoo! Research Barcelona lab, where we have been trying to improve search by applying ideas from computational linguistics.A key differentiating feature is that they extract entities from unstructured text, not just the semi-structured tables like FreeBase.
This comes on the heels of the ESAIR (Exploiting Semantic Annotations in Information Retrieval) 2009 workshop at WSDM.
Thanks to Iadh over the TerrierTeam blog for their coverage.