Triple

T19440009
Position Surface form Disambiguated ID Type / Status
Subject Rachel Ferrier E486324 entity
Predicate familyName P18 FINISHED
Object Ferrier 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: Ferrier | Statement: [Rachel Ferrier, familyName, Ferrier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferrier
Context triple: [Rachel Ferrier, familyName, Ferrier]
  • A. Ferrier
    Ferrier is a small commune located in northern Haiti, near the border with the Dominican Republic.
  • B. Ferrier chosen
    Ferrier is a surname of French origin borne by various notable individuals across fields such as science, politics, and the arts.
  • C. James Farrer
    James Farrer was a 19th-century British antiquarian and politician known for his early archaeological excavations in Orkney, Scotland.
  • D. Will Farnaby
    Will Farnaby is the cynical journalist and publicist who serves as the central viewpoint character in Aldous Huxley’s utopian novel "Island."
  • E. Farrer
    Farrer is an Australian federal electoral division in New South Wales, encompassing large rural and regional areas in the state’s southwest.
  • 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_69d8e8d7ad488190a3373045029b0f3b completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63364371081908e899c2a47af4e5d completed April 20, 2026, 2:08 p.m.
Created at: April 10, 2026, 1:38 p.m.