Triple

T12148834
Position Surface form Disambiguated ID Type / Status
Subject Game of Death E289399 entity
Predicate starring P1507 FINISHED
Object Robert Wall E270133 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 Wall | Statement: [Game of Death, starring, Robert Wall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Wall
Context triple: [Game of Death, starring, Robert Wall]
  • A. Robert Wall chosen
    Robert Wall is a British actor and martial artist best known for appearing in several Bruce Lee films, including "Enter the Dragon" and "Way of the Dragon."
  • B. Eric Waller
    Eric Waller is an entrepreneur best known as a co-founder of the mobile-focused ticketing platform SeatGeek.
  • C. Michael Wallis
    Michael Wallis is an American historian and author best known for his works on Route 66 and the American West, as well as for voicing the Sheriff in Pixar’s Cars films.
  • D. Michael Wall
    Michael Wall is a biotechnology entrepreneur best known as the founder of the biopharmaceutical company Alkermes.
  • E. Robert Walls
    Robert Walls is a former Australian rules football player and premiership-winning coach best known for his coaching stints with several VFL/AFL clubs, including the Brisbane Bears.
  • 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_69d6ab4c6710819097a9d228382dde43 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915ad6ef08190b334a97d6ab41487 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f698c5648190a5a29e08f2b7d8ab completed May 2, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:49 p.m.