Triple

T18402412
Position Surface form Disambiguated ID Type / Status
Subject Doubtless Bay E450028 entity
Predicate nearbySettlement P350 FINISHED
Object Mangonui 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: Mangonui | Statement: [Doubtless Bay, nearbySettlement, Mangonui]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangonui
Context triple: [Doubtless Bay, nearbySettlement, Mangonui]
  • A. Mangonui chosen
    Mangonui is a small historic coastal town in New Zealand known for its scenic harbour, fishing heritage, and popular waterfront fish and chip shops.
  • B. Tangowahine
    Tangowahine is a small rural locality in New Zealand’s Northland Region, situated within the Kaipara District.
  • C. Waitahuna
    Waitahuna is a small rural settlement in the Otago region of New Zealand, historically associated with gold mining and farming.
  • D. Pātea
    Pātea is a small coastal town in South Taranaki, New Zealand, known for its historic freezing works and its strong Māori cultural heritage.
  • E. Tapanui
    Tapanui is a small rural town in South Otago, New Zealand, known historically for forestry and farming.
  • 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_69e519537eb88190bc85d21471e27c26 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.