Overview

Kensho NERD (Named Entity Recognition and Disambiguation) is a cutting-edge machine learning system that unlocks the full potential of your textual data by linking it to existing sources of structured knowledge. Trained on millions of business-related documents, NERD is the only technology on the market specifically optimized to extract financial entity information from text documents.

With NERD you can:

• Uncover the companies, subsidiaries, and other financial organizations that appear in your textual data, powering smart search and supercharged research workflows
• Link those entities to their entries in S&P Global's rich Capital IQ database, augmenting your textual data by making new connections and enabling deeper insights
• Leverage the unique power of NERD's AI to find people, places, and events with NERD's Wikimedia engine, which links to a broad knowledge base containing tens of millions of entities

Discover powerful synergies when you combine NERD with other Kensho AI-enabled services, including Extract, Link, and Scribe.

For a full product overview, please visit our profile page (opens in a new tab) on the S&P Marketplace.

Get Started

To sign up, please email support@kensho.com to set up your API profile.

Once signed up, you can begin using NERD in seconds via our REST API, where we expose both synchronous and asynchronous endpoints for real-time and batch processing use cases.

To start annotating documents with NERD, use the Authentication Quickstart guide to generate an Access Token.

If your use case requires that you authenticate via a keypair (for example, if you are running NERD in a production service), visit the Advanced Authentication guide.

Token in hand, visit the Text Annotation Guide to submit text documents for entity extraction.

For more information, you can reference the full API Documentation or check out our series of video guides (opens in a new tab) to help with getting started.