Triple

T22971446
Position Surface form Disambiguated ID Type / Status
Subject Ossie E571196 entity
Predicate hasNotableBearer P458 FINISHED
Object Ossie Davis 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: Ossie Davis | Statement: [Ossie, hasNotableBearer, Ossie Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ossie Davis
Context triple: [Ossie, hasNotableBearer, Ossie Davis]
  • A. Ossie Davis chosen
    Ossie Davis was an acclaimed American actor, director, playwright, and civil rights activist known for his powerful performances on stage and screen and his outspoken commitment to social justice.
  • B. Ossie Davis Jr.
    Ossie Davis Jr. is an American actor and the son of legendary performers Ossie Davis and Ruby Dee, known in part for his former marriage to actress Rae Dawn Chong.
  • C. Merle Harmon
    Merle Harmon was an American sportscaster best known for his play-by-play work on Major League Baseball and NFL broadcasts over several decades.
  • D. Cicely Tyson
    Cicely Tyson was an acclaimed American actress renowned for her powerful, trailblazing portrayals of strong Black women in film, television, and theater.
  • E. John Amos
    John Amos is an American actor best known for his roles in the television series "Good Times" and the miniseries "Roots."
  • 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_69e245b2c6548190a0e4c7f2f7df2d48 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1823370fc819084a13d6e4eb6e44e completed April 29, 2026, 3:59 a.m.
Created at: April 17, 2026, 3:48 p.m.