Triple

T15654370
Position Surface form Disambiguated ID Type / Status
Subject Oakey E376392 entity
Predicate locatedWestOf P4239 FINISHED
Object Toowoomba E15092 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: Toowoomba | Statement: [Oakey, locatedWestOf, Toowoomba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toowoomba
Context triple: [Oakey, locatedWestOf, Toowoomba]
  • A. Toowoomba chosen
    Toowoomba is a major regional city on the Darling Downs in eastern Australia, known for its gardens, annual Carnival of Flowers, and role as a service and education hub for southern Queensland.
  • B. Bundaberg
    Bundaberg is a coastal city in eastern Australia known for its sugarcane industry, rum distillery, and proximity to the southern Great Barrier Reef.
  • C. Rockhampton
    Rockhampton is a regional city in central Queensland, Australia, known as a major agricultural and beef production hub along the Fitzroy River.
  • D. Goondiwindi
    Goondiwindi is a rural town in southwestern Queensland, Australia, known as an agricultural and transport hub near the New South Wales border.
  • E. Kingaroy
    Kingaroy is a rural town in Queensland, Australia, known as a major peanut-growing center and service hub for the surrounding agricultural region.
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef089948190902ec22f4d7bc932 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff7569d30c8190a711d78d05e9b8c5 completed May 9, 2026, 5:56 p.m.
Created at: April 10, 2026, 4:15 a.m.