Triple

T15905360
Position Surface form Disambiguated ID Type / Status
Subject David Wingo E385697 entity
Predicate notableWork P4 FINISHED
Object Manglehorn E1017881 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: Manglehorn | Statement: [David Wingo, notableWork, Manglehorn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manglehorn
Context triple: [David Wingo, notableWork, Manglehorn]
  • A. Manglehorn chosen
    Manglehorn is a 2014 character-driven drama film directed by David Gordon Green and starring Al Pacino as a reclusive locksmith haunted by his past.
  • B. The Hayemaker
    The Hayemaker is the ring nickname of British former world heavyweight and cruiserweight boxing champion David Haye.
  • C. The Hoose-Gow
    The Hoose-Gow is a 1929 Laurel and Hardy short comedy film known for its prison-escape antics and slapstick humor.
  • D. The Elms
    The Elms is a grand Gilded Age mansion in Newport, Rhode Island, renowned for its opulent architecture and historic significance as a former summer residence of the American elite.
  • E. The Ghost in the Mill
    "The Ghost in the Mill" is a short ghost story by Harriet Beecher Stowe that blends New England folklore with moral and religious themes.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565956588190ba4726a2879b677d completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb0535a808190983b4ff028826cbf completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:52 a.m.