Triple

T1905660
Position Surface form Disambiguated ID Type / Status
Subject Arthur Conan Doyle E37996 entity
Predicate placeOfDeath P21 FINISHED
Object Crowborough E32634 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: Crowborough | Statement: [Arthur Conan Doyle, placeOfDeath, Crowborough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crowborough
Context triple: [Arthur Conan Doyle, placeOfDeath, Crowborough]
  • A. Crowborough chosen
    Crowborough is a small town in East Sussex, England, known for its elevated position on the High Weald and its association with Sir Arthur Conan Doyle.
  • B. Narborough
    Narborough is a village in the English county of Norfolk, known for its rural setting and historic parish character.
  • C. Fulbourn
    Fulbourn is a village and civil parish located just southeast of Cambridge in the district of South Cambridgeshire, England.
  • D. Braughing
    Braughing is a historic rural village in Hertfordshire, England, known for its traditional architecture and long-established community.
  • E. Buntingford
    Buntingford is a small historic market town in Hertfordshire, England, known for its traditional high street and rural surroundings.
  • 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_69a8862a26088190aae5243695aeefc0 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb191b710819091a5b767550fcf61 completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69adeaf944c881908c5cb54bd27d6fa9 completed March 8, 2026, 9:32 p.m.
Created at: March 4, 2026, 7:35 p.m.