Triple

T19811285
Position Surface form Disambiguated ID Type / Status
Subject Mangere Bridge E475950 entity
Predicate connects P390 FINISHED
Object Māngere 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: Māngere | Statement: [Mangere Bridge, connects, Māngere]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Māngere
Context triple: [Mangere Bridge, connects, Māngere]
  • A. Māngere chosen
    Māngere is a suburb of Auckland, New Zealand, known for its proximity to Auckland Airport and its culturally diverse community.
  • B. Takapuna
    Takapuna is a coastal suburb on Auckland’s North Shore in New Zealand, known for its popular beach, shopping precinct, and recreational amenities.
  • C. Mount Roskill
    Mount Roskill is a suburban area and volcanic cone in Auckland, New Zealand, known for its diverse community and residential character.
  • D. Pukekohe
    Pukekohe is a town in the Auckland Region of New Zealand, known for its rich agricultural land and motor racing circuit.
  • E. Remuera
    Remuera is an affluent residential suburb in Auckland, New Zealand, known for its leafy streets, historic homes, and proximity to the city centre.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6542bd7a48190acf67db41f1131c9 completed April 20, 2026, 4:28 p.m.
Created at: April 10, 2026, 1:50 p.m.