Triple

T5100313
Position Surface form Disambiguated ID Type / Status
Subject Down E114965 entity
Predicate contains P35 FINISHED
Object Comber E413145 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: Comber | Statement: [Down, contains, Comber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Comber
Context triple: [Down, contains, Comber]
  • A. Comber chosen
    Comber is a small town in Northern Ireland known for its historic links to the linen industry and its location near Strangford Lough in County Down.
  • B. Humberston
    Humberston is a coastal village and civil parish in North East Lincolnshire, England, known for its proximity to the North Sea and the nearby resort of Cleethorpes.
  • C. Combe
    Combe is a small rural village in Oxfordshire, England, known for its traditional English countryside character and proximity to the River Evenlode.
  • D. Chatteris
    Chatteris is a small market town in the Fenland district of Cambridgeshire, England, known for its agricultural surroundings and historic parish church.
  • E. Seacombe
    Seacombe is a riverside district and ferry terminal on the Wirral Peninsula in England, serving as a key Mersey crossing point to Liverpool.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd758381dc8190ac491788d27ab8e0 completed March 20, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba8977f481908b0d55a9cd28d492 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:40 p.m.