Triple

T3847671
Position Surface form Disambiguated ID Type / Status
Subject Usain Bolt E85210 entity
Predicate sponsoredBy P67 FINISHED
Object Puma E23437 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: Puma | Statement: [Usain Bolt, sponsoredBy, Puma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puma
Context triple: [Usain Bolt, sponsoredBy, Puma]
  • A. Puma chosen
    Puma is a major German sportswear and athletic footwear brand known for its performance-oriented shoes, apparel, and collaborations with high-profile athletes and designers.
  • B. Diadora
    Diadora is an Italian sportswear and footwear brand known for producing football kits, athletic shoes, and apparel for various professional teams and athletes.
  • C. Bata
    Bata is a major port city on the mainland of Equatorial Guinea, serving as a key economic and transportation hub for the country.
  • D. Onitsuka Tiger
    Onitsuka Tiger is a Japanese athletic footwear and apparel brand known for its retro-styled sneakers and as the predecessor to the modern ASICS corporation.
  • E. Adidas
    Adidas is a global sportswear and equipment company known for its iconic three-stripe branding and production of athletic footwear, apparel, and accessories.
  • 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_69aed936de1c81908f91bed80f70abb2 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeebcc8a0481909c35161336bdfbf9 completed March 9, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b50414acdc81909bf0b62afa3fe536 completed March 14, 2026, 6:45 a.m.
Created at: March 9, 2026, 3:18 p.m.