Triple

T15026381
Position Surface form Disambiguated ID Type / Status
Subject Lethal Weapon 3 E378226 entity
Predicate screenwriter P2831 FINISHED
Object Robert Mark Kamen E673171 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: Robert Mark Kamen | Statement: [Lethal Weapon 3, screenwriter, Robert Mark Kamen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Mark Kamen
Context triple: [Lethal Weapon 3, screenwriter, Robert Mark Kamen]
  • A. Robert Mark Kamen chosen
    Robert Mark Kamen is an American screenwriter and producer best known for creating and writing hit action franchises such as The Karate Kid and Taken.
  • B. Daniel Kerr
    Daniel Kerr is a former Australian rules footballer best known for his career with the West Coast Eagles in the AFL.
  • C. Jason Kingsley
    Jason Kingsley is a British entrepreneur and game developer best known as the co-founder and CEO of the video game studio Rebellion Developments.
  • D. Stephen Harrison
    Stephen Harrison is a film editor known for his work on classic British cinema, including the historical drama "The Private Life of Henry VIII."
  • E. Christopher Henderson
    Christopher Henderson is a fictional high-ranking counterterrorism operative and former mentor to Jack Bauer in the television series "24."
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7dfcb508190aec8cd667e27a8ea completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fea5b0bbf4819082e14715bfd6003d completed May 9, 2026, 3:10 a.m.
Created at: April 10, 2026, 2:58 a.m.