Triple

T828563
Position Surface form Disambiguated ID Type / Status
Subject Light Dragoons E17911 entity
Predicate garrison P75 FINISHED
Object Catterick Garrison E75293 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: Catterick Garrison | Statement: [Light Dragoons, garrison, Catterick Garrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catterick Garrison
Context triple: [Light Dragoons, garrison, Catterick Garrison]
  • A. Catterick Garrison chosen
    Catterick Garrison is a major British Army base in North Yorkshire, England, and one of the largest military garrisons in the United Kingdom.
  • B. Rosyth
    Rosyth is a Scottish port town on the north shore of the Firth of Forth, known for its naval dockyard and ferry connections.
  • C. Moore Barracks
    Moore Barracks is a British military installation named in honor of Sir John Moore, a renowned general of the Napoleonic Wars.
  • D. Aldershot
    Aldershot is a town in Hampshire, England, historically known as a major British Army garrison and military center.
  • E. RAF Brize Norton
    RAF Brize Norton is the Royal Air Force’s largest station in the UK, serving as its main air transport and air-to-air refuelling hub.
  • 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_69a4937c9c188190aaa216f6b466f452 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ab99b1e48190afad1f073348b29a completed March 1, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d97a3b08190b7a5c635d74bcd47 completed March 3, 2026, 11:24 p.m.
Created at: March 1, 2026, 7:38 p.m.