Triple

T19105813
Position Surface form Disambiguated ID Type / Status
Subject John Johnston Duddy E467650 entity
Predicate nickname P55 FINISHED
Object Jackie NE NERFINISHED

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: Jackie | Statement: [John Johnston Duddy, nickname, Jackie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jackie
Context triple: [John Johnston Duddy, nickname, Jackie]
  • A. Jackie
    Jackie is the central protagonist of the film "Love Lies Bleeding," around whom the movie’s intense, character-driven narrative revolves.
  • B. Jackie chosen
    Jackie is the nickname of John Jackie Duddy, a young Northern Irish man remembered as the first person shot dead on Bloody Sunday in Derry in 1972.
  • C. Jackie
    Jackie is a biographical drama film in which Natalie Portman portrays Jacqueline Kennedy in the aftermath of President John F. Kennedy’s assassination.
  • D. Jackie
    "Jackie" is an album, likely in the pop or R&B genre, best known for featuring the song "I Bet."
  • E. Jackie
    "Jackie" is a stage play by Elfriede Jelinek that portrays the life and public image of Jacqueline Kennedy Onassis, in which actress Blair Brown delivered a notable performance.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e37159688190a6896d9730214ba8 completed April 20, 2026, 8:27 a.m.
Created at: April 10, 2026, 12:04 p.m.