Triple

T4672246
Position Surface form Disambiguated ID Type / Status
Subject RJR Nabisco E103590 entity
Predicate keyExecutive P256 FINISHED
Object Henry Kravis E126259 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Henry Kravis | Statement: [RJR Nabisco, keyExecutive, Henry Kravis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry Kravis
Context triple: [RJR Nabisco, keyExecutive, Henry Kravis]
  • A. Henry Kravis chosen
    Henry Kravis is an American billionaire businessman and co-founder of the private equity firm Kohlberg Kravis Roberts & Co. (KKR), known as a pioneer of leveraged buyouts.
  • B. Robert Kravis
    Robert Kravis is a film producer best known for his work on the crime thriller "Lucky Number Slevin."
  • C. Howard Ratner
    Howard Ratner is a fast-talking, compulsive New York City jeweler and gambling addict whose risky schemes drive the intense, chaotic plot of the film *Uncut Gems*.
  • D. Felix Fuld
    Felix Fuld was a prominent American businessman and co-founder of the Newark-based department store Bamberger's, later part of Macy's.
  • E. Howard Lutnick
    Howard Lutnick is an American businessman best known as the longtime chairman and CEO who rebuilt the financial services firm Cantor Fitzgerald after the September 11 attacks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd43dda32c8190938b37744ca270fc completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6351ca8c8190871b9bebdb7ab88d completed March 20, 2026, 3:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69be039538048190b4075daf47355cee completed March 21, 2026, 2:33 a.m.
Created at: March 20, 2026, 1:15 p.m.