Triple

T15377705
Position Surface form Disambiguated ID Type / Status
Subject Agent Whiskey E367711 entity
Predicate worksWith P398 FINISHED
Object Eggsy Unwin E49510 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: Eggsy Unwin | Statement: [Agent Whiskey, worksWith, Eggsy Unwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eggsy Unwin
Context triple: [Agent Whiskey, worksWith, Eggsy Unwin]
  • A. Gary "Eggsy" Unwin chosen
    Gary "Eggsy" Unwin is a street-smart British youth who becomes a highly skilled gentleman spy in the Kingsman film series.
  • B. Harvey Ackroyd
    Harvey Ackroyd was an architect known for his work on the Tennessee State Capitol.
  • C. Guy Fleegman
    Guy Fleegman is a comedic supporting character in the sci-fi parody film "Galaxy Quest," known for his self-aware fear of being the expendable "redshirt" crew member.
  • D. Jack Kitchin
    Jack Kitchin was a film editor known for his work on early Hollywood productions, including classic musicals of the 1930s.
  • E. Charles Butterworth
    Charles Butterworth was an American comic film actor of the 1930s and early 1940s, known for his dry, dithering persona in numerous Hollywood comedies.
  • 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_69d85a1551a08190ba2caea7cd51c639 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e5ece1081908d7c1289258b9c1f completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b56dd1c81909a3933330e85fe0e completed May 9, 2026, 10:24 a.m.
Created at: April 10, 2026, 3:18 a.m.