Triple

T22317432
Position Surface form Disambiguated ID Type / Status
Subject Al Kaline E551683 entity
Predicate nickname P55 FINISHED
Object Mr. Tiger 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: Mr. Tiger | Statement: [Al Kaline, nickname, Mr. Tiger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mr. Tiger
Context triple: [Al Kaline, nickname, Mr. Tiger]
  • A. Mr. Tiger chosen
    Mr. Tiger is the nickname of Al Kaline, the Hall of Fame right fielder who became a legendary figure for the Detroit Tigers in Major League Baseball.
  • B. Doc the Tiger
    Doc the Tiger is the costumed tiger mascot representing Towson University's women's basketball team and broader athletic programs.
  • C. Tiger Tim
    Tiger Tim is the nickname of Tim Henman, a former British professional tennis player known for his success at Wimbledon and role in revitalizing British tennis in the 1990s and early 2000s.
  • D. Old Tige
    Old Tige was the nickname of William L. Cabell, a Confederate general who later became a prominent postwar civic leader and mayor of Dallas, Texas.
  • E. Le Tigre
    Le Tigre was the fierce political nickname of French statesman Georges Clemenceau, reflecting his combative and determined leadership style, especially during World War I.
  • 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_69e11e4776588190abb21e5cea79973f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157543d688190a151fade71880131 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:42 p.m.