Triple

T20944970
Position Surface form Disambiguated ID Type / Status
Subject Tangerine Bowl E515821 entity
Predicate formerNameOf P65 FINISHED
Object Citrus Bowl 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: Citrus Bowl | Statement: [Tangerine Bowl, formerNameOf, Citrus Bowl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Citrus Bowl
Context triple: [Tangerine Bowl, formerNameOf, Citrus Bowl]
  • A. Citrus Bowl chosen
    The Citrus Bowl is a long-standing annual college football bowl game traditionally held in Orlando, Florida.
  • B. Tampa Bay Bowl
    The Tampa Bay Bowl is a long-running college football postseason bowl game held annually in the Tampa Bay area of Florida.
  • C. Gator Bowl
    The Gator Bowl is a long-running annual college football bowl game traditionally played in Jacksonville, Florida.
  • D. GoDaddy.com Bowl
    The GoDaddy.com Bowl was a postseason college football bowl game played annually in Mobile, Alabama, featuring teams from the Football Bowl Subdivision.
  • E. Orange Bowl
    The Orange Bowl is one of college football’s oldest and most prestigious postseason bowl games, traditionally held in the Miami area and often featuring top-ranked teams.
  • 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_69e0b4fc13408190b06868df03c5c29b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fad705e481909da0098d7c73cd02 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 12:55 p.m.