Triple

T22024068
Position Surface form Disambiguated ID Type / Status
Subject Larry Poons E543914 entity
Predicate givenName P17 FINISHED
Object Larry 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: Larry | Statement: [Larry Poons, givenName, Larry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry
Context triple: [Larry Poons, givenName, Larry]
  • A. Larry
    Larry is the sarcastic and somewhat cynical cameraman who works alongside Phil Connors in the film "Groundhog Day."
  • B. Larry
    Larry is the given name of Larry Berra, better known as Yogi Berra, the legendary American baseball catcher and manager.
  • C. Larry chosen
    Larry is a common masculine given name, often a diminutive of Lawrence, used widely in English-speaking countries.
  • D. Larry
    Larry is the given name of Larry Holmes, the American former professional boxer and longtime world heavyweight champion.
  • E. Larry
    Larry is the given name of Larry L. King, an American playwright, journalist, and author best known for co-writing the musical "The Best Little Whorehouse in Texas."
  • 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127ca45a08190b2d5d3a8eb37cb4b completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:23 p.m.