Google has been experimenting with semantic search for a while, i.e search for the query "~what is the capital of France?" and you get a semantic search. Or try "~who is the president of nigeria?"
I recently came across, a new application from a subsidiary of Thomson Reuters called Open Calais. It is free, has an api, and is a semantic application that actually works. It describes itself as follows:
It looks at unstructured data and pulls out content that is separated into the three classes of content it recognises: named entities, facts, and events, as shown in the diagram below.
The OpenCalais Web Service automatically creates rich semantic metadata for the content you submit – in well under a second. Using natural language processing (NLP), machine learning and other methods, Calais analyzes your document and finds the entities within it. But, Calais goes well beyond classic entity identification and returns the facts and events hidden within your text as well.
The tags are delivered to you; you can then incorporate them into other applications - for search, news aggregation, blogs, catalogs, you name it.
Watch the video below (apologies for the cheesiness), and play with their simulator. More information at Open Calais