Triple

T21850304
Position Surface form Disambiguated ID Type / Status
Subject Coleen Rowley E539486 entity
Predicate sharedAwardWith P15164 FINISHED
Object Cynthia Cooper NE NERFINISHED

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: Cynthia Cooper | Statement: [Coleen Rowley, sharedAwardWith, Cynthia Cooper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cynthia Cooper
Context triple: [Coleen Rowley, sharedAwardWith, Cynthia Cooper]
  • A. Cynthia Cooper
    Cynthia Cooper is a Hall of Fame American basketball player best known as a star guard and multiple-time WNBA champion and Finals MVP with the Houston Comets.
  • B. Cynthia Cooper chosen
    Cynthia Cooper is an American accountant and whistleblower best known for exposing the WorldCom accounting fraud scandal.
  • C. Gayle Wilmore
    Gayle Wilmore is the birth name of Gayle Laakmann McDowell, a prominent software engineer, author, and founder best known for her technical interview preparation books such as "Cracking the Coding Interview."
  • D. Teresa Weatherspoon
    Teresa Weatherspoon is a Hall of Fame American basketball player and coach best known as an original WNBA star and defensive standout at point guard.
  • E. Leona Rhule
    Leona Rhule is the daughter of American football coach Matt Rhule.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c476c3c88190a92d08ebb59a128a completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0bd582ca48190890648fdee2a0c6e completed April 28, 2026, 1:59 p.m.
Created at: April 16, 2026, 6:56 p.m.