Triple

T14766363
Position Surface form Disambiguated ID Type / Status
Subject Benched E347005 entity
Predicate starring P1507 FINISHED
Object Jay Harrington E978313 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: Jay Harrington | Statement: [Benched, starring, Jay Harrington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jay Harrington
Context triple: [Benched, starring, Jay Harrington]
  • A. Jay Harrington chosen
    Jay Harrington is an American actor best known for his lead role on the sitcom "Better Off Ted" and his work in television dramas such as "S.W.A.T."
  • B. Patrick Hallahan
    Patrick Hallahan is an American drummer best known as a longtime member of the rock band My Morning Jacket.
  • C. Jonathan Hackett
    Jonathan Hackett is an actor best known for his role in Lars von Trier’s acclaimed 1996 drama film "Breaking the Waves."
  • D. Jeffrey Harrington
    Jeffrey Harrington is a central character on the television drama "The Haves and the Have Nots," known for his complex personal struggles and evolving relationships within the show's web of wealth, power, and family conflict.
  • E. J. P. Harrington
    J. P. Harrington was an American linguist and ethnographer renowned for his extensive early 20th-century documentation of Native American languages and cultures.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f576c881909da70627f5897c94 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef5e176081909e822881a866ecec completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 1:30 a.m.