Triple

T20506241
Position Surface form Disambiguated ID Type / Status
Subject Kooyong, Victoria E503436 entity
Predicate nearbySuburb P41355 FINISHED
Object Toorak 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: Toorak | Statement: [Kooyong, Victoria, nearbySuburb, Toorak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toorak
Context triple: [Kooyong, Victoria, nearbySuburb, Toorak]
  • A. Toorak chosen
    Toorak is an affluent inner suburb of Melbourne, Australia, known for its grand homes, high-end shopping, and status as one of the city's most prestigious residential areas.
  • B. Prahran
    Prahran is an inner-city suburb of Melbourne, Australia, known for its vibrant shopping, dining, and nightlife precincts along Chapel Street.
  • C. Brookvale
    Brookvale is a residential suburb within the town of Runcorn in Cheshire, England.
  • D. Brookvale
    Brookvale is a suburb that serves as the local setting for the Brookvale Community Centre, providing residential, recreational, and community services.
  • E. Morphett Vale
    Morphett Vale is a large southern suburb of Adelaide in South Australia, known as one of the state’s earliest and most populous residential areas.
  • 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_69e0b4b1e52c8190894281cf7e3283ab completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69dc66f00819083c804535e045545 completed April 20, 2026, 9:42 p.m.
Created at: April 16, 2026, 11:35 a.m.