From the introduction page:
The free OpenCalais service and open API is the fastest way to tag the people, places, facts and events in your content. It can help you improve your SEO, increase your reader engagement, create search-engine-friendly ‘topic hubs’ and streamline content operations – saving you time and money.
OpenCalais is free to use in both commercial and non-commercial settings, but can only be used on public content (don’t run your confidential or competitive company information through it!). OpenCalais does not keep a copy of your content, but it does keep a copy of the metadata it extracts there from.
To repeat, OpenCalais is not a private service, and there is no secure, enterprise version that you can buy to operate behind a firewall. It is your responsibility to police the content that you submit, so make sure you are comfortable with our Terms of Service (TOS) before you jump in.
You can process up to 50,000 documents per day (blog posts, news stories, Web pages, etc.) free of charge. If you need to process more than that – say you are an aggregator or a media monitoring service – then see this page to learn about Calais Professional. We offer a very affordable license.
OpenCalais’ early adopters include CBS Interactive / CNET, Huffington Post, Slate, Al Jazeera, The New Republic, The White House and more. Already more than 30,000 developers have signed up, and more than 50 publishers and 75 entrepreneurs are using the free service to help build their businesses.
You can read about the pioneering work of these publishers, entrepreneurs and developers here.
To get started, scroll to the bottom section of this page. To build OpenCalais into an existing site or publishing platform (CMS), you will need to work with your developers.
I thought I had written about OpenCalais but it turns out it was just in quotes in other posts. Should know better than to rely on my memory. 😉
The 50,000 document per day limit sounds reasonable to me and should be enough for some interesting experiments. Perhaps even comparisons of the results from different tagging projects.
Not to say one is better than another but to identify spots on semantic margins where ambiguity may be found.
Historical documents should make interesting test subjects.
Being cautious the further back in history we reach, the less meaningful it is to say a word has a “correct” meaning. An author used it with a particular meaning but that passed from our ken with the passing of the author and their linguistic community. We can guess what may have been meant, but nothing more.