From the post:
This morning we upgraded OpenCalais to release 4.7. Our focus with 4.7 was on a significant improvement in the detection and disambiguation of companies as well as some behind-the-scenes tune-ups and bug fixes.
If your content contains company names you should already be seeing a significant improvement in detection and disambiguation. While company detection has always been very good in OpenCalais, now it’s great.
If you’re one of our high-volume commercial clients (1M+ transactions per day), we’ll be rolling out your upgrade toward the end of the month.
And, remember, you can always drop by the OpenCalais viewer for a quick test or exploration of OpenCalais with zero programming involved.
If you don’t already know OpenCalais:
From a user perspective it’s pretty simple: You hand the Web Service unstructured text (like news articles, blog postings, your term paper, etc.) and it returns semantic metadata in RDF format. What’s happening in the background is a little more complicated.
Using natural language processing and machine learning techniques, the Calais Web Service examines your text and locates the entities (people, places, products, etc.), facts (John Doe works for Acme Corporation) and events (Jane Doe was appointed as a Board member of Acme Corporation). Calais then processes the entities, facts and events extracted from the text and returns them to the caller in RDF format.
Please also check out the Calais blog and forums to see where Calais is headed. Significant development activities include the ability for downstream content consumers to retrieve previously generated metadata using a Calais-provided GUID, additional input languages, and user-defined processing extensions.
Did I mention it is a free service up to 50,000 submissions a day? (see the license terms for details)
OpenCalais won’t capture every entity or relationship known to you but it will do a lot of the rote work for you. You can then fill in the specialized parts.