Triple

T5373864
Position Surface form Disambiguated ID Type / Status
Subject Joe Maddon E108913 entity
Predicate familyName P18 FINISHED
Object Maddon E108913 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: Maddon | Statement: [Joe Maddon, familyName, Maddon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maddon
Context triple: [Joe Maddon, familyName, Maddon]
  • A. Maddon chosen
    Maddon is the surname of Joe Maddon, a prominent American Major League Baseball manager best known for leading the Chicago Cubs to their 2016 World Series title.
  • B. Grady Little
    Grady Little is an American former Major League Baseball manager best known for his controversial handling of the Boston Red Sox pitching staff during the 2003 postseason.
  • C. Francona
    Francona is a surname most prominently associated with American baseball figures Tito (Terry) Francona and his father John Francona.
  • D. Gary Moeller
    Gary Moeller was an American football coach best known for leading the University of Michigan Wolverines in the early 1990s after serving as a longtime assistant under Bo Schembechler.
  • E. Bart Andrus
    Bart Andrus is an American football coach best known for his work in NFL Europe and various professional and collegiate coaching roles.
  • 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd86ad820081908763765dcbc99cbf completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf293ba6a08190bcbecf465e4e5881 completed March 21, 2026, 11:26 p.m.
Created at: March 20, 2026, 2:03 p.m.