Triple

T17890577
Position Surface form Disambiguated ID Type / Status
Subject Ella Craig E447303 entity
Predicate relative P37 FINISHED
Object Fiona Loudon 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: Fiona Loudon | Statement: [Ella Craig, relative, Fiona Loudon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fiona Loudon
Context triple: [Ella Craig, relative, Fiona Loudon]
  • A. Fiona Loudon chosen
    Fiona Loudon is a Scottish actress best known as the former wife of actor Daniel Craig and the mother of their daughter, Ella Craig.
  • B. Fiona Campbell
    Fiona Campbell is the romantic Scottish heroine of the classic musical "Brigadoon," known for her deep connection to the enchanted village that appears for only one day every hundred years.
  • C. Fiona Lewis
    Fiona Lewis is a British actress and writer best known for her roles in 1970s horror and thriller films.
  • D. Fiona Hartnett
    Fiona Hartnett is a notable individual recognized for achievements significant enough to be distinctly associated with the Hartnett surname.
  • E. Fiona Caldwell
    Fiona Caldwell is a television executive producer known for her work on the documentary travel series "Great American Railroad Journeys."
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d7948888190b59ddc7061d13e84 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:18 a.m.