Triple

T1140482
Position Surface form Disambiguated ID Type / Status
Subject Puma E23437 entity
Predicate competitor P1375 FINISHED
Object Under Armour E23649 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: Under Armour | Statement: [Puma, competitor, Under Armour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Under Armour
Context triple: [Puma, competitor, Under Armour]
  • A. Under Armour chosen
    Under Armour is an American sportswear and athletic footwear company known for its performance apparel and innovative moisture-wicking fabrics.
  • B. Reebok
    Reebok is a global athletic footwear and apparel brand known for its sportswear, fitness-focused products, and collaborations in running, training, and lifestyle markets.
  • C. Adidas
    Adidas is a global sportswear and equipment company known for its iconic three-stripe branding and production of athletic footwear, apparel, and accessories.
  • D. Nike, Inc.
    Nike, Inc. is a multinational corporation best known as one of the world’s leading designers, marketers, and distributors of athletic footwear, apparel, and sports equipment.
  • E. Authentic Brands Group
    Authentic Brands Group is a brand management company that acquires, develops, and licenses a portfolio of well-known consumer and lifestyle brands.
  • 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_69a493ef399c8190b04b9146d2314f59 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc290ae08190afbf7e7ea2100d9e completed March 1, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac59b020d48190bc6ecbdb720c6779 completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:44 p.m.