Triple

T12623044
Position Surface form Disambiguated ID Type / Status
Subject Holbrook E301435 entity
Predicate locatedNear P294 FINISHED
Object Shotley E299734 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: Shotley | Statement: [Holbrook, locatedNear, Shotley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shotley
Context triple: [Holbrook, locatedNear, Shotley]
  • A. Shotley chosen
    Shotley is a village and civil parish located on the Shotley Peninsula in Suffolk, eastern England, overlooking the confluence of the Rivers Orwell and Stour.
  • B. Gamesley
    Gamesley is a residential area and former council estate on the outskirts of Glossop in Derbyshire, England.
  • C. Shottesbrooke
    Shottesbrooke is a small rural parish and village in Berkshire, England, noted for its historic church and estate.
  • D. Butleigh
    Butleigh is a village in Somerset, England, historically associated with notable figures such as Admiral Samuel Hood, 1st Viscount Hood.
  • E. Howley
    Howley is an English surname most notably associated with William Howley, a 19th-century Archbishop of Canterbury.
  • 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_69d7bdeaf49c8190b13800111fa77ea3 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d960c8671881909a102d28b0e7f603 completed April 10, 2026, 8:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ed6f79881908872c644a9789f04 completed May 2, 2026, 8:30 p.m.
Created at: April 9, 2026, 5:14 p.m.