Triple

T911203
Position Surface form Disambiguated ID Type / Status
Subject John Cotton E19661 entity
Predicate familyName P18 FINISHED
Object Cotton E3906 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: Cotton | Statement: [John Cotton, familyName, Cotton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cotton
Context triple: [John Cotton, familyName, Cotton]
  • A. Cotton chosen
    Cotton is a soft, natural fiber harvested from the seed pods of cotton plants and widely used in textiles and clothing.
  • B. Cotton Caligula A.ix
    Cotton Caligula A.ix is a medieval manuscript in the British Library that preserves one of the principal surviving copies of the Middle English poem "The Owl and the Nightingale."
  • C. Glycine max
    Glycine max is the cultivated soybean plant, a major legume crop grown worldwide for its protein- and oil-rich seeds used in food, feed, and industrial products.
  • D. Cottonopolis
    Cottonopolis is a historical nickname for Manchester, England, reflecting its prominence as a major center of the cotton and textile industry during the Industrial Revolution.
  • E. Bagassa
    Bagassa is a small genus of tropical trees in the mulberry family, known for species such as Bagassa guianensis found in South American rainforests.
  • 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_69a4939f91a08190ba68c2c81eab90fe completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b2de5b008190851852331db41324 completed March 1, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c73d5bdc8190828cdf9f54e33a46 completed March 4, 2026, 5:46 a.m.
Created at: March 1, 2026, 7:39 p.m.