Triple

T16193443
Position Surface form Disambiguated ID Type / Status
Subject Red River (1948 film) E392999 entity
Predicate mainCharacter P1183 FINISHED
Object Matthew Garth E767470 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: Matthew Garth | Statement: [Red River (1948 film), mainCharacter, Matthew Garth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Garth
Context triple: [Red River (1948 film), mainCharacter, Matthew Garth]
  • A. Matthew Garth chosen
    Matthew Garth is a central fictional cowboy and adopted son figure in the classic 1948 Western film "Red River," portrayed by Montgomery Clift.
  • B. Hunter McEwan
    Hunter McEwan is an individual notable enough to be recognized as a prominent bearer of the surname McEwan.
  • C. Charles Blake
    Charles Blake is a pragmatic and progressive government official in Downton Abbey who becomes a significant love interest and intellectual match for Lady Mary Crawley.
  • D. Graydon Carter
    Graydon Carter is a Canadian-born journalist and longtime editor of Vanity Fair, known for his influential role in media and culture.
  • E. Ethan Tarrant
    Ethan Tarrant is a central character in the horror film "Candyman: Farewell to the Flesh," involved in uncovering the dark legacy and truth behind the Candyman legend.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222d74d788190a637fdb9b4f184b9 completed April 17, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffff0bfd08819083afc4bea1b99aad completed May 10, 2026, 3:44 a.m.
Created at: April 10, 2026, 5:02 a.m.