Triple

T11931815
Position Surface form Disambiguated ID Type / Status
Subject Rudyard Kipling E283931 entity
Predicate child P120 FINISHED
Object Elsie Kipling E283931 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: Elsie Kipling | Statement: [Rudyard Kipling, child, Elsie Kipling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elsie Kipling
Context triple: [Rudyard Kipling, child, Elsie Kipling]
  • A. Elsie Kipling chosen
    Elsie Kipling was the daughter of British author and Nobel laureate Rudyard Kipling.
  • B. Josephine Kipling
    Josephine Kipling was one of the daughters of English writer Rudyard Kipling and the sister of Elsie Kipling.
  • C. Alice Kipling
    Alice Kipling was the mother of British author Rudyard Kipling and a member of the prominent Macdonald family, which was closely connected to several notable Victorian artists and writers.
  • D. Nigel Kipling
    Nigel Kipling is a sharp-tongued, stylish and supportive fashion editor in "The Devil Wears Prada" who mentors the protagonist within the cutthroat world of high fashion.
  • E. Millicent Bagnold
    Millicent Bagnold is a former British Minister for Magic in the Harry Potter universe, best known for overseeing the wizarding world during Voldemort’s first downfall.
  • 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_69d6ab2ce9c48190b5d39511b524f666 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d90305015c81908edb0d9d3d012b2e completed April 10, 2026, 2:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f458a576fc8190b68b27365cd53caf completed May 1, 2026, 7:39 a.m.
Created at: April 8, 2026, 9:45 p.m.