Triple

T23204448
Position Surface form Disambiguated ID Type / Status
Subject Dan Jenkins E580410 entity
Predicate notableWork P4 FINISHED
Object Semi-Tough 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: Semi-Tough | Statement: [Dan Jenkins, notableWork, Semi-Tough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Semi-Tough
Context triple: [Dan Jenkins, notableWork, Semi-Tough]
  • A. Semi-Tough chosen
    Semi-Tough is a 1977 sports comedy film that satirizes professional football and 1970s self-help culture, starring Burt Reynolds, Kris Kristofferson, and Jill Clayburgh.
  • B. Too Tough
    Too Tough is a track featured on the hip-hop album "Undercover."
  • C. The Hard
    The Hard is a waterfront area in Portsmouth, England, known as a major transport hub and gateway to the city’s historic dockyard and ferry services.
  • D. The Tough Ones
    The Tough Ones is a 1970s Italian poliziottesco crime-action film known for its gritty violence, tough cop antihero, and cult status among Eurocrime cinema fans.
  • E. Down and Dirty
    Down and Dirty is a shared-world superhero anthology novel in the Wild Cards series, featuring interconnected stories about people transformed by an alien virus.
  • 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_69e24602ae1481908aaa6bc7ca493867 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1907b3e88819088a397a99456bf77 completed April 29, 2026, 5 a.m.
Created at: April 17, 2026, 4:07 p.m.