Triple

T22794557
Position Surface form Disambiguated ID Type / Status
Subject George Rooke E564206 entity
Predicate familyName P18 FINISHED
Object Rooke 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: Rooke | Statement: [George Rooke, familyName, Rooke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rooke
Context triple: [George Rooke, familyName, Rooke]
  • A. Rooke chosen
    Rooke is a surname of English origin borne by various notable individuals across fields such as engineering, the military, and the arts.
  • B. Rockliffe
    Rockliffe is a masculine given name most notably borne by early 20th-century Canadian-born silent film actor Rockliffe Fellowes.
  • C. D’Ascoyne
    D’Ascoyne is the aristocratic family in the British black comedy film "Kind Hearts and Coronets," whose members are systematically murdered by the vengeful protagonist to claim a dukedom.
  • D. Crowel
    Crowel is an alternative spelling of the surname Crowell, which is of English origin.
  • E. James Rooke
    James Rooke was a British military officer best known for leading the British Legion during the Napoleonic-era campaigns in South America for independence.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cd81794819091b528600e322d7b completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.