Triple

T3051204
Position Surface form Disambiguated ID Type / Status
Subject Fences (2016 film) E83574 entity
Predicate starring P1507 FINISHED
Object Mykelti Williamson E38461 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: Mykelti Williamson | Statement: [Fences (2016 film), starring, Mykelti Williamson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mykelti Williamson
Context triple: [Fences (2016 film), starring, Mykelti Williamson]
  • A. Mykelti Williamson chosen
    Mykelti Williamson is an American actor best known for his roles in films such as "Forrest Gump," where he played Bubba, and numerous television series.
  • B. Warrick Brown
    Warrick Brown is a fictional crime scene investigator and forensic analyst on the television series "CSI: Crime Scene Investigation."
  • C. Muhammad Wilkerson
    Muhammad Wilkerson is an American former NFL defensive end best known for his Pro Bowl tenure with the New York Jets after a standout college career at Temple University.
  • D. Lamar Williams
    Lamar Williams was an American bassist best known for his work with the Allman Brothers Band in the 1970s, where he helped shape their Southern rock sound.
  • E. Jason Williams
    Jason Williams is a former American NBA point guard known for his flashy playmaking and crowd-pleasing style, particularly during his time with the Sacramento Kings.
  • 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_69ad8b24924c8190a9bb6f61d519e4ae completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9bf274f88190a759f9ce3da47c35 completed March 8, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1eefa84f08190a178cc0674d8a3ab completed March 11, 2026, 10:38 p.m.
Created at: March 8, 2026, 3:01 p.m.