Triple

T21702845
Position Surface form Disambiguated ID Type / Status
Subject Central Auckland E535696 entity
Predicate hasPart P35 FINISHED
Object Eden Terrace 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: Eden Terrace | Statement: [Central Auckland, hasPart, Eden Terrace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eden Terrace
Context triple: [Central Auckland, hasPart, Eden Terrace]
  • A. Eden Terrace chosen
    Eden Terrace is an inner-city suburb of Auckland, New Zealand, known for its proximity to the central business district and mix of residential and commercial areas.
  • B. Kelvin Grove
    Kelvin Grove is an inner-city suburb of Brisbane, Australia, known for its mix of residential areas, educational institutions, and cultural facilities.
  • C. Kelvin Grove
    Kelvin Grove is a residential suburb located in the city of Palmerston North on New Zealand’s North Island.
  • D. Camberwell Green
    Camberwell Green is a small public park and historic civic space in the district of Camberwell in south London.
  • E. Southfields
    Southfields is a residential district in southwest London, England, known for its proximity to Wimbledon and its quiet, suburban character.
  • 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_69e0c46b44c0819088ab883ebd44e0e8 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef9b8161348190842c433531cfaa5b completed April 27, 2026, 5:23 p.m.
Created at: April 16, 2026, 6:46 p.m.