Triple

T22722168
Position Surface form Disambiguated ID Type / Status
Subject Kenneth E561889 entity
Predicate hasVariant P455 FINISHED
Object Kennett 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: Kennett | Statement: [Kenneth, hasVariant, Kennett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kennett
Context triple: [Kenneth, hasVariant, Kennett]
  • A. Kennett
    Kennett is a village in Cambridgeshire, England, known for its rural setting and railway station on the route between Ely and Ipswich.
  • B. Kennett chosen
    Kennett is an English-language surname borne by various notable individuals, including Australian politician Jeff Kennett.
  • C. Kennett Square, Pennsylvania
    Kennett Square, Pennsylvania is a small borough in southeastern Pennsylvania known as the "Mushroom Capital of the World" for its extensive mushroom farming industry.
  • D. Southcott
    Southcott is a researcher best known for formally describing the highly venomous box jellyfish species Chironex fleckeri.
  • E. Bottomley
    Bottomley is an English surname most notably associated with Horatio Bottomley, a prominent early 20th-century British financier, journalist, and politician.
  • 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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f17926ae0c8190af8493cab6b15261 completed April 29, 2026, 3:21 a.m.
Created at: April 17, 2026, 3:20 p.m.