Triple

T10722546
Position Surface form Disambiguated ID Type / Status
Subject The Tin Star E252857 entity
Predicate author P4 FINISHED
Object John W. Cunningham E310575 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: John W. Cunningham | Statement: [The Tin Star, author, John W. Cunningham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John W. Cunningham
Context triple: [The Tin Star, author, John W. Cunningham]
  • A. John W. Cunningham chosen
    John W. Cunningham was an American Western author best known for writing the short story that inspired the classic film "High Noon."
  • B. John Cunningham
    John Cunningham is a common personal name shared by numerous notable individuals across fields such as politics, sports, the arts, and academia.
  • C. Jack L. Murray
    Jack L. Murray is a film producer best known for his work on the 2009 horror remake "My Bloody Valentine 3D."
  • D. Thomas S. Gleason
    Thomas S. Gleason is an American politician who served as a member of the Massachusetts House of Representatives.
  • E. John L. Burns
    John L. Burns was a veteran of the War of 1812 who became famous as the elderly civilian sharpshooter who fought alongside Union troops during the Battle of Gettysburg in the American Civil War.
  • 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_69d6aa5d8be481909a43218b2bfdbe95 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d70d44d0048190a78aae2357e864a5 completed April 9, 2026, 2:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb08d63d481908ab1d5038424dab6 completed April 14, 2026, 9:24 p.m.
Created at: April 8, 2026, 9:13 p.m.