Triple

T23018579
Position Surface form Disambiguated ID Type / Status
Subject Hold Back the Night E573101 entity
Predicate mainCharacter P1183 FINISHED
Object Cpl. Danny "Irish" Young NE NERFINISHED

How this triple was built (3 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: Cpl. Danny "Irish" Young | Statement: [Hold Back the Night, mainCharacter, Cpl. Danny "Irish" Young]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cpl. Danny "Irish" Young
Context triple: [Hold Back the Night, mainCharacter, Cpl. Danny "Irish" Young]
  • A. Sgt. Francis Donovan
    Sgt. Francis Donovan is the central police sergeant character in the television drama series "Brooklyn South," which focuses on the lives and challenges of officers in a tough New York City precinct.
  • B. Sergeant Dan Scott
    Sergeant Dan Scott is a fictional police detective and sidekick to DCI Tom Barnaby in the British crime drama series "Midsomer Murders."
  • C. Sergeant John Kinley
    Sergeant John Kinley is the U.S. Army Special Forces soldier protagonist of Guy Ritchie's war drama "The Covenant," known for his bond with an Afghan interpreter during the Afghanistan conflict.
  • D. Sgt. Joe Broadhurst
    Sgt. Joe Broadhurst is a supporting police sergeant character on the 1970s American television crime drama "McCloud."
  • E. Sergeant Charles Enright
    Sergeant Charles Enright is a supporting police officer character in the 1970s American television crime drama series "McMillan & Wife."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cpl. Danny "Irish" Young
Target entity description: Cpl. Danny "Irish" Young is the tough, resourceful U.S. Marine protagonist of the Korean War film "Hold Back the Night," known for his leadership and resilience under fire.
  • A. Sgt. Francis Donovan
    Sgt. Francis Donovan is the central police sergeant character in the television drama series "Brooklyn South," which focuses on the lives and challenges of officers in a tough New York City precinct.
  • B. Sergeant Dan Scott
    Sergeant Dan Scott is a fictional police detective and sidekick to DCI Tom Barnaby in the British crime drama series "Midsomer Murders."
  • C. Sergeant John Kinley
    Sergeant John Kinley is the U.S. Army Special Forces soldier protagonist of Guy Ritchie's war drama "The Covenant," known for his bond with an Afghan interpreter during the Afghanistan conflict.
  • D. Sgt. Joe Broadhurst
    Sgt. Joe Broadhurst is a supporting police sergeant character on the 1970s American television crime drama "McCloud."
  • E. Sergeant Charles Enright
    Sergeant Charles Enright is a supporting police officer character in the 1970s American television crime drama series "McMillan & Wife."
  • F. None of above. chosen

Provenance (2 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.