Triple

T14120131
Position Surface form Disambiguated ID Type / Status
Subject John Darling E339881 entity
Predicate childOf P120 FINISHED
Object George Darling E1044501 NE FINISHED

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: George Darling | Statement: [John Darling, childOf, George Darling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Darling
Context triple: [John Darling, childOf, George Darling]
  • A. George Darling chosen
    George Darling is a character in J.M. Barrie’s Peter Pan stories, portrayed as the somewhat stern but ultimately loving father of Wendy, John, and Michael Darling.
  • B. Henry Darling
    Henry Darling is a lesser-known relative of British Army officer and former New South Wales Governor Sir Ralph Darling.
  • C. Albert Brisbane
    Albert Brisbane was a 19th-century American social theorist and reformer who popularized Charles Fourier’s utopian socialist ideas in the United States.
  • D. Sylvia Llewelyn Davies
    Sylvia Llewelyn Davies was the real-life mother of the boys who inspired J. M. Barrie’s Peter Pan and a central figure in the story behind his creation of Neverland.
  • E. Harold Crick
    Harold Crick is the meticulous IRS auditor and unsuspecting protagonist of the metafictional film "Stranger Than Fiction," whose life begins mirroring a narrated novel.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de60942a588190beff0058a92f7051 completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0bc60088190a7e2f0c9532304e3 completed May 7, 2026, 5:49 p.m.
Created at: April 9, 2026, 10:22 p.m.