Triple

T18401737
Position Surface form Disambiguated ID Type / Status
Subject Kaipara District E450012 entity
Predicate hasSuburbOrLocality P76817 FINISHED
Object Matakohe 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: Matakohe | Statement: [Kaipara District, hasSuburbOrLocality, Matakohe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matakohe
Context triple: [Kaipara District, hasSuburbOrLocality, Matakohe]
  • A. Matakohe chosen
    Matakohe is a small rural settlement in New Zealand best known for its Kauri Museum and historic connections to the kauri gum and timber industries.
  • B. Rangitihi
    Rangitihi is a revered Polynesian ancestor regarded as a key progenitor of many Te Arawa tribal lineages in Aotearoa New Zealand.
  • C. Utupua
    Utupua is a small, remote island in the Santa Cruz Islands group of the Solomon Islands in the South Pacific Ocean.
  • D. Onehunga
    Onehunga is a suburb of Auckland, New Zealand, known for its diverse multicultural community and strong Pacific Island, particularly Tongan, presence.
  • E. Tamaūpoko
    Tamaūpoko is a Māori iwi (tribe) of the central North Island of New Zealand, traditionally associated with the Whanganui region.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5195185b08190bd3b5471cdc047b0 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.