Triple

T3430867
Position Surface form Disambiguated ID Type / Status
Subject Backdraft 2 E72332 entity
Predicate stars P1956 FINISHED
Object Donald Sutherland E86440 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: Donald Sutherland | Statement: [Backdraft 2, stars, Donald Sutherland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Sutherland
Context triple: [Backdraft 2, stars, Donald Sutherland]
  • A. Donald Sutherland chosen
    Donald Sutherland is a renowned Canadian actor known for his versatile performances in films such as M*A*S*H, Klute, Ordinary People, and The Hunger Games series.
  • B. Sam Waterston
    Sam Waterston is an American actor known for his distinguished film, television, and stage career, including prominent roles in productions such as Law & Order and The Killing Fields.
  • C. Michael York
    Michael York is an English actor known for his roles in films such as "Cabaret," "Logan's Run," and the "Austin Powers" series.
  • D. Richard Crenna
    Richard Crenna was an American actor and director known for his roles in films such as the "Rambo" series and numerous television shows including "The Real McCoys."
  • E. Robert Culp
    Robert Culp was an American actor best known for his charismatic leading roles in 1960s television, particularly in stylish espionage and crime dramas.
  • 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_69ad85ae14308190bcbc25cfa0246c0b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb9bd61908190a7bdd01f24334fc3 completed March 8, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3547b1b3481909646bf36e8461ff4 completed March 13, 2026, 12:04 a.m.
Created at: March 8, 2026, 3:15 p.m.