Triple

T18674465
Position Surface form Disambiguated ID Type / Status
Subject Balmoral, Auckland E456562 entity
Predicate adjacentTo P224 FINISHED
Object Mount Roskill 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: Mount Roskill | Statement: [Balmoral, Auckland, adjacentTo, Mount Roskill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mount Roskill
Context triple: [Balmoral, Auckland, adjacentTo, Mount Roskill]
  • A. Mount Roskill chosen
    Mount Roskill is a suburban area and volcanic cone in Auckland, New Zealand, known for its diverse community and residential character.
  • B. Mount Albert
    Mount Albert is a parliamentary electorate in Auckland, New Zealand, known for being represented by prominent Labour Party leaders including former Prime Minister Jacinda Ardern.
  • C. Mount Albert
    Mount Albert is a volcanic peak and residential suburb in Auckland, New Zealand, known for its prominent scoria cone and surrounding urban community.
  • D. Mount Albert
    Mount Albert is a small rural community in the town of East Gwillimbury, Ontario, known for its village character and surrounding farmland.
  • E. Māngere
    Māngere is a suburb of Auckland, New Zealand, known for its proximity to Auckland Airport and its culturally diverse community.
  • 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_69d8d38f72b4819090a935175d9ca8af completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e556b4e390819091ad9dd118ca1f4f completed April 19, 2026, 10:27 p.m.
Created at: April 10, 2026, 11:48 a.m.