Triple

T23028397
Position Surface form Disambiguated ID Type / Status
Subject DuPont Experimental Station E573388 entity
Predicate associatedWith P37 FINISHED
Object Kevlar 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: Kevlar | Statement: [DuPont Experimental Station, associatedWith, Kevlar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevlar
Context triple: [DuPont Experimental Station, associatedWith, Kevlar]
  • A. Kevlar chosen
    Kevlar is a high-strength, lightweight synthetic fiber widely used in bulletproof vests, protective gear, and industrial applications for its exceptional durability and resistance to impact and heat.
  • B. Nylon
    Nylon is a family of synthetic polymers widely used as strong, lightweight fibers and plastics in textiles, engineering components, and consumer products.
  • C. Cordura
    Cordura is a durable performance fabric brand known for its high-strength, abrasion-resistant textiles widely used in outdoor gear, military equipment, and workwear.
  • D. Tyvek
    Tyvek is a durable, lightweight, synthetic material widely used for protective garments, packaging, and weather-resistant building wraps.
  • E. Nomex
    Nomex is a high-performance, flame-resistant aramid fiber widely used in protective clothing and industrial applications for its heat and fire resistance.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1847f453881909a8f2affb48c64f1 completed April 29, 2026, 4:09 a.m.
Created at: April 17, 2026, 3:52 p.m.