Frequently Asked Questions
How does it work?
For the user, the process is pretty simple. You feed unstructured text into the extraction engine (news articles, blog postings, etc.). Open Calais analyzes your text, processes the extracted information, and returns semantic metadata in the RDF, JSON, or N3 format.
What does metadata mean? What is metadata tagging?
Metadata is “data about data.” For example, the title and author of a book is metadata about the book. In information systems, a tag is a non-hierarchical keyword or term assigned to a piece of information (such as an Internet bookmark, a digital image, or a computer file). This kind of metadata helps describe an item and allows it to be found again by browsing or searching.
Metadata can describe many different kinds of information. For example within the Metadata Service, metadata could describe:
- Entities: (Companies, people, places, products, etc.)
- Relationships: (John Doe works for Acme Corp.)
- Facts: (John Doe is a 42-year old, male CFO.)
- Events: (Jane Doe was appointed a Board member of Acme Corp.)
- Topics: (Story is about M&As in the Pharma industry)
By tagging various details you can start creating a strong metadata store which can be constantly maintained and searched for intelligent insight.
Who is the typical Open Calais user?
Our users run the gamut from bloggers to investment bankers. What they have in common is an enormous volume of data and the desire to extract intelligence from it.
What is Open Calais? And why is it offered for free?
Open Calais is a free service currently accessible via a public website (opencalais.com) and will also be available via a Thomson Reuters sponsored public website called PermID.org. This free service provides document tagging using an extensive set of fields such as Company, Person, Geography, Industry Classifications, Topics, Social Tags, Facts, and Events. The service is hosted by Thomson Reuters and allows users to upload up to 5,000 documents a day.
Why is Open Calais better than other tagging services?
Open Calais tagging regularly yields relevancy scores of 90% or more – a metric which is far superior to other tagging services on the market. Furthermore, Open Calais metadata is an instance of Thomson Reuters entities, which themselves are curated by thousands of Thomson Reuters employees, ensuring the highest quality metadata.
I have been using Open Calais since before 2015; how do I upgrade to the new and enhanced Open Calais?
The Upgrade page on opencalais.com will tell you everything you need to know about upgrading to the new Open Calais.
Where can I read about the differences between the legacy Open Calais and the new Open Calais?
The Open Calais Upgrade Guide (available on the Upgrade page of opencalais.com) details the differences, and the Open Calais blog has regularly published posts informing our users of new developments, including highlights of the new Open Calais.
What is Thomson Reuters Intelligent Tagging and how is it different from Open Calais?
Thomson Reuters Intelligent Tagging is a version of Open Calais that is geared specifically toward professionals who want to get more out of our service than Open Calais offers. If you are in financial services and, in addition to entities, people, events and topics, would like to obtain additional enhanced metadata, then we invite you to visit our Products page for more information.
Where can I find developer documentation for Open Calais?
The API User Guide is available on the API page of opencalais.com.
The legacy opencalais.com has a Forums portal that can answer many of your questions regarding our services or can act as a place simply for you to share your opinion on how we’re doing.
How does Open Calais link to permIDs?
Open Calais metadata is supported by the Thomson Reuters entity masters and these entities are delivered to you via the Thomson Reuters Permanent Identifier or PermID.
The PermID is a machine readable, 64-bit number used to create a unique reference to a piece of information. The PermID will never change over time. PermID is progressively being introduced to our desktop and data-feed products as well as to web services like Open Calais.
The value of PermID is immense. It complements Open Calais in that it is meant to bring alignment to data that is disorganized. Leverage PermID to bring even more meaning to the data you are extracting with Open Calais.
What is a permID URI?
The Thomson Reuters Permanent Identifier or PermID is a machine readable, 64 bit number used to create a unique reference to a piece of information. A PermID will never change over time. Behind the scenes, Open Calais leverages the PermID for tagging organizations, people, and other entities.
We provide no-cost access to PermID’s via the Open PermID initiative, which also includes the Open Calais tagging capability that fully leverages PermID’s. On this site, each PermID is mapped to its own URI, which can be leveraged by the Open Calais tagging API to extract even more information on your tagged entities.
Register for your API token to see how PermID URI’s can enhance your tagging experience.