Triple

T16813125
Position Surface form Disambiguated ID Type / Status
Subject Larry Kellner E408665 entity
Predicate name P16 FINISHED
Object Larry Kellner 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 Kellner | Statement: [Larry Kellner, name, Larry Kellner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry Kellner
Context triple: [Larry Kellner, name, Larry Kellner]
  • A. Larry Kellner chosen
    Larry Kellner is an American business executive best known for leading Continental Airlines as its chief executive officer.
  • B. Larry Kehres
    Larry Kehres is a highly successful American college football coach best known for leading the University of Mount Union to multiple NCAA Division III national championships and establishing one of the most dominant programs in the sport’s history.
  • C. Barry Kroeger
    Barry Kroeger was an American character actor known for his distinctive villainous roles in mid-20th-century film and television.
  • D. Larry Kolber
    Larry Kolber is a songwriter best known for co-writing pop hits in the 1960s, often in collaboration with fellow composer Jack Keller.
  • E. Vince Kehres
    Vince Kehres is an American football coach best known for leading the University of Mount Union’s powerhouse Division III program to multiple national championships.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b2df5c888190a462614e1432c357 completed April 18, 2026, 4:35 p.m.
Created at: April 10, 2026, 5:23 a.m.