i202 Fall 2009 School of Information, UC Berkeley

 According to this article, it looks like there is some movement on creating a semantic web search, though the article writer seems a bit skeptical of its ability to deliver. T2 (a new project by the makers of Twine), which may come out by the end of the year, is hoping to index the top few dozen sites in major categories. Interestingly, T2 will be adding the semantic tags, not the owners of the sites themselves. However, they are creating developer tools like an ontologies editor in order to make T2's automatic semantic tags more accurate: "There can literally be hundreds of thousands of ontologies for every conceivable topic. If Twine knows what ontology to apply to a given Web page, it can do a better job applying semantic tags to it and extracting data."

I guess a good question is if semantic data can ever be very accurate it if is tagged by a machine, let alone if the data is tagged by a third party rather than the content creators themselves.