Identity Resolver


Leave routine data gathering to AI so that analysts can use their expertise to make connections

Overview

Boost the effectiveness of every analyst

Your most experienced analyst is dramatically more effective and knowledgeable than your least experienced analyst. Increase the effectiveness of every analyst with Rosette® Identity Resolver, which captures and shares out the institutional knowledge and subject matter expertise of your entire enterprise as analysts curate and make connections only possible with their knowledge.

Authoritative identities are the known people, places, and organizations of interest listed in your knowledge base. A knowledge base is only useful if users find what they are looking for and are thus encouraged to spend time adding new information.

With Identity Resolver, you can:

  • Let AI tirelessly mine incoming data streams to automatically match entity mentions and their context to knowledge base entries
  • Enable subject matter experts to use their expertise to easily curate and connect knowledge base entries and capture their institutional knowledge
  • Discover “ghosts” — the entities unknown to your knowledge base – by tracking them across hundreds of sources before promoting them to an authoritative identity
  • Enrich and reveal the relationships and sentiments between your identities
  • Eliminate the need for complex queries, let AI address the variety, ambiguity, and language challenges in your data.

Product highlights

  • 21 supported languages
  • 29 supported entity types and 450+ subtypes
  • Fast and scalable
  • Industrial-strength support
  • Cloud and enterprise deployments

How It Works

How the knowledge base self-learns

Rosette® Identity Resolver processes unstructured text and discovers the authoritative identities (real-life people, places. organizations) you care about across multiple languages through entity extraction. Using contextual information around an entity mention (people, places. organizations), Identity Resolver will link each entity within incoming data to an identity in your knowledge base through entity linking and fuzzy name matching.

For example, depending on context, “George Bush” might refer to the 43rd President of the United States (“George Bush was sworn in as president on January 20, 1989.”) or the Nimitz-class aircraft carrier CVN 77 (“The George Bush sailed into Norfolk.”).

How to capture institutional knowledge and expertise

You can only know what you know, so how can you leverage all the expertise in your organization? For most,even if “Parvinder Choudhary” of Punjab and “Parvinder Chowdhuri” of Himachal Pradesh have similar backgrounds, they may seem like different people. Your team’s India expert, though, would know that in 1966, the province of Punjab was divided into the three modern-day provinces of Haryana, Himachal Pradesh, and Punjab, and that “Choudhary” and “Chowdhuri” are variants of the same surname.

Using Identity Resolver’s user-friendly curation tools, the India expert can hand-link “Parvinder Choudhary” of Punjab as an alias of “Parvinder Chowdhuri” of Himachal Pradesh, thus increasing the intelligence of the knowledge base about Parvinder – photos, aliases, attributes, and network connections. The increased context enables the system to more accurately link data about Parvinder going forward.

How ghost detection works

A paradox of intelligence work is you simply don’t know what you don’t know. When the Identity Resolver comes across an identity that isn’t in your knowledge base, it will automatically create a ghost representing that new identity. As the system continues to process data, it will associate relevant data, associations, and relationships about each ghost. When enough data accumulates a human analyst can promote the ghost to an authoritative identity, which the system will prefer to link to, over a ghost identity.