Triple

T2215522
Position Surface form Disambiguated ID Type / Status
Subject Jane Bennet – Susannah Harker E48022 entity
Predicate createdBy P806 FINISHED
Object Andrew Davies E48018 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: Andrew Davies | Statement: [Jane Bennet – Susannah Harker, createdBy, Andrew Davies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Davies
Context triple: [Jane Bennet – Susannah Harker, createdBy, Andrew Davies]
  • A. Andrew Davies chosen
    Andrew Davies is a renowned British screenwriter celebrated for his acclaimed television adaptations of classic literature, including numerous works by Jane Austen.
  • B. Eoin Colfer
    Eoin Colfer is an Irish author best known for creating the popular Artemis Fowl series of children's fantasy novels.
  • C. Graham Carr
    Graham Carr is a Canadian academic and administrator who serves as the president of Concordia University in Montreal.
  • D. Alan Webber
    Alan Webber is an American politician and former business magazine co-founder who serves as the mayor of Santa Fe, New Mexico.
  • E. Charles Foster
    Charles Foster is one of the children of acclaimed American actress and filmmaker Jodie Foster.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbff11574819091d1b50d637ae767 completed March 7, 2026, 6:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6afa4f4481908cd1559624805559 completed March 9, 2026, 6:38 a.m.
Created at: March 4, 2026, 7:46 p.m.