Triple

T4476310
Position Surface form Disambiguated ID Type / Status
Subject Jake Peralta E100016 entity
Predicate admires P28362 FINISHED
Object John McClane E433178 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: John McClane | Statement: [Jake Peralta, admires, John McClane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John McClane
Context triple: [Jake Peralta, admires, John McClane]
  • A. John McClane chosen
    John McClane is the tough, wisecracking New York cop and everyman action hero famously portrayed by Bruce Willis in the Die Hard film series.
  • B. John McClain
    John McClain was a screenwriter active in classic Hollywood cinema, known for his work on mid-20th-century American films.
  • C. John McClain
    John McClain is a music industry executive and record producer best known as a co-founder of Interscope Records and for managing and working with major artists.
  • D. William Cage
    William Cage is the protagonist of the science fiction film "Edge of Tomorrow," a military public relations officer who becomes caught in a time loop while fighting an alien invasion.
  • E. Harry Callahan
    Harry Callahan is a fictional tough, rule-bending San Francisco police inspector famously portrayed by Clint Eastwood in the "Dirty Harry" film series.
  • 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_69b34553cbe48190afa8ac1cac285b86 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b356d8600c8190a8b812889c50f144 completed March 13, 2026, 12:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6288434188190a23c48267f55ce1e completed March 15, 2026, 3:33 a.m.
Created at: March 12, 2026, 11:35 p.m.