Triple

T2304945
Position Surface form Disambiguated ID Type / Status
Subject AWST E51816 entity
Predicate usedInCity P4810 FINISHED
Object Bunbury E51812 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: Bunbury | Statement: [AWST, usedInCity, Bunbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bunbury
Context triple: [AWST, usedInCity, Bunbury]
  • A. Bunbury chosen
    Bunbury is a coastal city in Western Australia known as a regional port and commercial hub south of Perth.
  • B. Farnum
    Farnum is a locality within Providence County, Rhode Island, likely a small village or neighborhood rather than an incorporated city.
  • C. Marple
    Marple is a suburban town in the Metropolitan Borough of Stockport, Greater Manchester, England, known for its canals, locks, and proximity to the Peak District.
  • D. Fosby
    Fosby is a settlement that serves as the main local hub and seat of administration for the surrounding Aremark area in Norway.
  • E. Corringham
    Corringham is a small town and civil parish in the unitary authority of Thurrock in Essex, England, with historic roots and a largely residential character.
  • 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_69a88b0bb30c81908ded03b006d29387 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc60300388190993bed7d312a92d5 completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f3579248190829a07fe508d72a7 completed March 9, 2026, 8:05 a.m.
Created at: March 4, 2026, 7:49 p.m.