Triple

T20282321
Position Surface form Disambiguated ID Type / Status
Subject Porirua Basin E503179 entity
Predicate nearbyTown P3883 FINISHED
Object Tawa 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: Tawa | Statement: [Porirua Basin, nearbyTown, Tawa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tawa
Context triple: [Porirua Basin, nearbyTown, Tawa]
  • A. Rakaia
    Rakaia is a small rural town in Canterbury, New Zealand, known for its proximity to the Rakaia River and its strong agricultural and fishing activities.
  • B. Wainuiomata chosen
    Wainuiomata is a residential suburb in the Wellington Region of New Zealand, situated in a valley east of Lower Hutt and known for its strong community character and surrounding bush-clad hills.
  • C. Waiau
    Waiau is a small rural town in New Zealand’s South Island, situated in the Hurunui District of the Canterbury region.
  • D. Nakaseke
    Nakaseke is a district in central Uganda that lies within the traditional kingdom of Buganda.
  • E. Owaka
    Owaka is a small rural town in New Zealand’s Catlins region, known as a gateway to the area’s rugged coastline and native forests.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6768f86448190842389a98b93a918 completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 10:39 a.m.