Triple

T2246236
Position Surface form Disambiguated ID Type / Status
Subject Gary "Eggsy" Unwin E49510 entity
Predicate mentor P3665 FINISHED
Object Harry Hart E48818 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: Harry Hart | Statement: [Gary "Eggsy" Unwin, mentor, Harry Hart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Hart
Context triple: [Gary "Eggsy" Unwin, mentor, Harry Hart]
  • A. Harry Hart chosen
    Harry Hart is a suave, highly skilled British secret agent and mentor figure in the Kingsman film series.
  • B. Lee Chandler
    Lee Chandler is the emotionally withdrawn Boston janitor and handyman at the center of the film "Manchester by the Sea," whose tragic past drives the movie’s exploration of grief and guilt.
  • C. Vincent Winter
    Vincent Winter was a Scottish child actor who gained prominence in the 1950s and 1960s, later working behind the scenes in film production.
  • D. Michael Connelly
    Michael Connelly is a bestselling American crime fiction author best known for his Harry Bosch and Lincoln Lawyer series.
  • E. Raymond Gardner
    Raymond Gardner was the brother of famed American actress Ava Gardner, a member of the Gardner family from rural North Carolina.
  • 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_69a88aa979788190ad6500f1d8eee2fc completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0ea75d881909d4e176a432f32e8 completed March 7, 2026, 6:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71c1edd081909acbb8b1915ce0d6 completed March 9, 2026, 7:07 a.m.
Created at: March 4, 2026, 7:47 p.m.