Triple

T22103767
Position Surface form Disambiguated ID Type / Status
Subject Deborra-Lee Furness E546234 entity
Predicate familyName P18 FINISHED
Object Furness 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: Furness | Statement: [Deborra-Lee Furness, familyName, Furness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Furness
Context triple: [Deborra-Lee Furness, familyName, Furness]
  • A. Furness chosen
    Furness is an English-origin surname borne by various notable figures, including scholars, architects, and public officials.
  • B. Furness
    Furness is a peninsula and historic region in Cumbria, England, known for its industrial heritage, coastal landscapes, and proximity to the Lake District.
  • C. Furness Vale
    Furness Vale is a small village in Derbyshire, England, situated in the High Peak area of the Peak District.
  • D. Barrow and Furness
    Barrow and Furness is a UK parliamentary constituency in Cumbria that includes the industrial town of Barrow-in-Furness and surrounding areas.
  • E. Fearnhead
    Fearnhead is a suburban residential area within the town of Warrington in Cheshire, England.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129175a7881909549883f23c53dca completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.