Triple

T10355284
Position Surface form Disambiguated ID Type / Status
Subject Dead Man Walking E243984 entity
Predicate castMember P1668 FINISHED
Object Robert Prosky E517152 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 Prosky | Statement: [Dead Man Walking, castMember, Robert Prosky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Prosky
Context triple: [Dead Man Walking, castMember, Robert Prosky]
  • A. Robert Prosky chosen
    Robert Prosky was an American character actor known for his warm, authoritative presence in film, television, and theater, with notable roles in works like "Hill Street Blues," "Broadcast News," and numerous stage productions.
  • B. John Grono
    John Grono was a Welsh-born Australian sealer, shipbuilder, and explorer active in the early 19th century, noted for his voyages around New Zealand and the naming of several coastal features.
  • C. Michael Siberry
    Michael Siberry is an Australian actor known for his work in theatre, television, and film, including roles in British and American productions.
  • D. Gregg Turkington
    Gregg Turkington is an American comedian, actor, and writer best known for his abrasive anti-comedy persona Neil Hamburger and his work on projects like "On Cinema."
  • E. Greg Morrisett
    Greg Morrisett is a computer scientist known for his work on programming languages and type systems, particularly in the design of safe and secure systems.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e953d4888190b7ca0ac932349dbf completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d750a9b4188190a8ecdd9e4d97570b completed April 9, 2026, 7:09 a.m.
Created at: April 6, 2026, 11:58 a.m.