Triple

T22844729
Position Surface form Disambiguated ID Type / Status
Subject Mount Stuart (Queensland) E566182 entity
Predicate locatedIn P40 FINISHED
Object City of Townsville NE NERFINISHED

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: City of Townsville | Statement: [Mount Stuart (Queensland), locatedIn, City of Townsville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of Townsville
Context triple: [Mount Stuart (Queensland), locatedIn, City of Townsville]
  • A. City of Townsville chosen
    The City of Townsville is a local government area in North Queensland, Australia, centered on the coastal city of Townsville, a major regional hub for industry, defense, and education.
  • B. Southwoods City
    Southwoods City is a large mixed-use township development in the Philippines featuring residential, commercial, and leisure components.
  • C. Coronet City
    Coronet City is the bustling capital and primary urban center of the planet Corellia in the Star Wars universe.
  • D. Mistralton City
    Mistralton City is a foggy, aviation-themed city in the Unova region of the Pokémon world, known for its airport and Flying-type Gym.
  • E. Advancetown
    Advancetown is a rural locality in the Gold Coast hinterland of Queensland, Australia, known for its surrounding forests, reservoirs, and outdoor recreation areas.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245869e188190a196584f36e682da completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e8726d4819095b4d999b4172ff7 completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:36 p.m.