Triple

T22278566
Position Surface form Disambiguated ID Type / Status
Subject Devonshire family E550670 entity
Predicate familyName P18 FINISHED
Object Cavendish 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: Cavendish | Statement: [Devonshire family, familyName, Cavendish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cavendish
Context triple: [Devonshire family, familyName, Cavendish]
  • A. Cavendish
    Cavendish is a picturesque village and civil parish in Suffolk, England, noted for its historic thatched cottages and traditional English countryside charm.
  • B. Cavendish
    Cavendish is the married surname of Kathleen Kennedy, a member of the prominent Kennedy family who became Marchioness of Hartington.
  • C. Cavendish chosen
    Cavendish is a prominent English aristocratic family historically influential in politics, science, and society, associated with figures such as scientists Henry and William Cavendish and the Dukes of Devonshire.
  • D. Yates
    Yates is a surname of English origin borne by various notable individuals across literature, politics, sports, and other fields.
  • E. Dunnet
    Dunnet is a small coastal village in the far north of Scotland, known for its sweeping sandy bay and proximity to Dunnet Head, the northernmost point of the British mainland.
  • 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_69e11e44d538819097c6b8f333af3352 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea96948819081c1ae6c7b11ab62 completed April 29, 2026, 12:19 a.m.
Created at: April 16, 2026, 8:40 p.m.