Triple

T19166909
Position Surface form Disambiguated ID Type / Status
Subject Mangere Mountain E469207 entity
Predicate hasViewOf P854 FINISHED
Object Manukau Harbour 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: Manukau Harbour | Statement: [Mangere Mountain, hasViewOf, Manukau Harbour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manukau Harbour
Context triple: [Mangere Mountain, hasViewOf, Manukau Harbour]
  • A. Manukau Harbour chosen
    Manukau Harbour is a large shallow natural harbour on the west coast of New Zealand’s North Island, forming one of the two main harbours of the Auckland region.
  • B. Manukau
    Manukau is a major urban area in South Auckland, New Zealand, known for its diverse population and role as a commercial and transport hub.
  • C. Waitangi Bay
    Waitangi Bay is a coastal inlet on the Chatham Islands of New Zealand that serves as the main harbour and maritime access point for the settlement of Waitangi.
  • D. Mangawhai Harbour
    Mangawhai Harbour is a coastal inlet on New Zealand’s North Island known for its sand dunes, tidal estuary, and popular recreational activities such as boating and fishing.
  • E. Waitematā Harbour
    Waitematā Harbour is the main natural harbour of Auckland, New Zealand, known for its scenic waterfront, busy shipping lanes, and iconic city skyline views.
  • 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_69d8dd09d5a081909ae43c286651ae5a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f16035b481908667a4415a1a63c9 completed April 20, 2026, 9:26 a.m.
Created at: April 10, 2026, 12:06 p.m.