Triple

T1717238
Position Surface form Disambiguated ID Type / Status
Subject DuPont E37316 entity
Predicate developed P73 FINISHED
Object Tyvek
Tyvek is a durable, lightweight, synthetic material widely used for protective garments, packaging, and weather-resistant building wraps.
 E192837 NE FINISHED

How this triple was built (4 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: Tyvek | Statement: [DuPont, developed, Tyvek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tyvek
Context triple: [DuPont, developed, Tyvek]
  • A. Acryllium
    Acryllium is a genus of guineafowl known for its strikingly patterned plumage and native range in sub-Saharan Africa.
  • B. Kapton
    Kapton is a high-performance polyimide film known for its exceptional thermal stability, electrical insulation, and durability in extreme environments such as outer space.
  • C. Kelty
    Kelty is a former coal-mining village in Fife, Scotland, situated near Lochgelly and close to the M90 motorway.
  • D. Pella Impervia
    Pella Impervia is a line of durable, fiberglass-framed windows and patio doors designed for strength, energy efficiency, and low maintenance.
  • E. Tulle
    Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tyvek
Triple: [DuPont, developed, Tyvek]
Generated description
Tyvek is a durable, lightweight, synthetic material widely used for protective garments, packaging, and weather-resistant building wraps.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tyvek
Target entity description: Tyvek is a durable, lightweight, synthetic material widely used for protective garments, packaging, and weather-resistant building wraps.
  • A. Acryllium
    Acryllium is a genus of guineafowl known for its strikingly patterned plumage and native range in sub-Saharan Africa.
  • B. Kapton
    Kapton is a high-performance polyimide film known for its exceptional thermal stability, electrical insulation, and durability in extreme environments such as outer space.
  • C. Kelty
    Kelty is a former coal-mining village in Fife, Scotland, situated near Lochgelly and close to the M90 motorway.
  • D. Pella Impervia
    Pella Impervia is a line of durable, fiberglass-framed windows and patio doors designed for strength, energy efficiency, and low maintenance.
  • E. Tulle
    Tulle is a historic town in central France, known as the capital of the Corrèze department in the Nouvelle-Aquitaine region.
  • F. None of above. chosen

Provenance (5 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_69a8861912dc8190931af43b4b9158a7 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63362ba481909e08e9f6fbf00b37 completed March 6, 2026, 5:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8ae6940c81909c1ebdfb0cdef5fc completed March 8, 2026, 2:42 p.m.
NEDg Description generation batch_69ad957adf1c8190b7c8656c1984f998 completed March 8, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ad97af6b388190b2af293599108df3 completed March 8, 2026, 3:37 p.m.
Created at: March 4, 2026, 7:30 p.m.