Triple

T14116658
Position Surface form Disambiguated ID Type / Status
Subject Always E339791 entity
Predicate competitor P1375 FINISHED
Object Kotex E726040 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: Kotex | Statement: [Always, competitor, Kotex]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kotex
Context triple: [Always, competitor, Kotex]
  • A. Kotex chosen
    Kotex is a well-known feminine hygiene brand offering products such as sanitary pads, tampons, and liners.
  • B. Sheex
    Sheex is a performance bedding company known for its athletic-inspired, moisture-wicking sheets and sleepwear.
  • C. Kleenex
    Kleenex is a widely recognized brand of facial tissues and related paper products known for being a generic term for disposable tissues.
  • D. Charmin
    Charmin is a popular brand of toilet paper known for its softness and comfort, produced by Procter & Gamble.
  • E. Wacoal
    Wacoal is a Japanese company best known as a leading manufacturer and retailer of women's lingerie and intimate apparel.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de6010a03c81909f5f160f8d1fa8fa completed April 14, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0baa328819099511dfa7b9666d3 completed May 7, 2026, 5:49 p.m.
Created at: April 9, 2026, 10:22 p.m.