Triple

T1149824
Position Surface form Disambiguated ID Type / Status
Subject Under Armour E23649 entity
Predicate hasKeyPerson P256 FINISHED
Object Kevin Plank E131884 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: Kevin Plank | Statement: [Under Armour, hasKeyPerson, Kevin Plank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevin Plank
Context triple: [Under Armour, hasKeyPerson, Kevin Plank]
  • A. Kevin Plank chosen
    Kevin Plank is an American entrepreneur best known as the founder and longtime CEO of the sportswear company Under Armour.
  • B. Andrew Marcus
    Andrew Marcus is a literary editor known for preparing an edition of E. M. Forster’s novel "Howards End."
  • C. Mark Parker
    Mark Parker is an American businessman best known for serving as the longtime CEO and later executive chairman of Nike, Inc.
  • D. Michael Kay
    Michael Kay is a New York sports broadcaster best known as the television play-by-play announcer for the New York Yankees and host of "The Michael Kay Show."
  • E. James Robinson
    James Robinson was a civil rights activist best known as one of the founders of the Congress of Racial Equality (CORE), a key organization in the U.S. civil rights movement.
  • 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_69a493f0d32c8190ac74bad3c87f2641 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc730b008190bd0901e0a47a4b7a completed March 1, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f139a008190a20f38330364dd2b completed March 7, 2026, 6:31 p.m.
Created at: March 1, 2026, 7:44 p.m.