Distinguishing Targets from Lookalikes: Entity Disambiguation Tactics and Examples

There are countless people and companies with identical names. As an investigator, how do you determine whether you’re looking at the right one?

Entity disambiguation, the process of distinguishing targets from others bearing the same name, is fundamental to investigative work but rarely taught outside of a limited set of targeting roles. This report offers four practical techniques and a series of illustrative examples investigators and analysts can use to more confidently and efficiently isolate their targets in a sea of lookalikes:

1. Unique Identifiers: Learn nuances in the identifier landscape that will help you better distinguish between unique and non-unique IDs.
2. Combinations of Non-Unique Identifiers: Understand which non-unique IDs will combine to give you the most confident disambiguations.
3. Relationship Co-Occurrence: Discover how links between entities can help you disambiguate in the absence of identifiers.
4. Name Frequency and Other Contextual Factors: Explore how circumstantial probability can help confirm a suspected disambiguation.

Sayari provides global corporate transparency and supply chain risk identification for government and industry. Its commercial risk intelligence software harvests comprehensive corporate and trade data from more than 250 jurisdictions worldwide and surfaces previously hidden risk insights in an intuitive network analysis platform.

Since its founding in 2015, Sayari has earned the trust of top financial institutions, Fortune 100 corporations and government agencies, securing a $40M Series C in 2021. Sayari is headquartered in Washington, D.C., and its solutions are used by more than 3,000 frontline analysts in 35 countries.