Triple

T21730757
Position Surface form Disambiguated ID Type / Status
Subject Port Hacking E536398 entity
Predicate adjacentTo P224 FINISHED
Object Cronulla 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: Cronulla | Statement: [Port Hacking, adjacentTo, Cronulla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cronulla
Context triple: [Port Hacking, adjacentTo, Cronulla]
  • A. Cronulla chosen
    Cronulla is a coastal suburb in southern Sydney, Australia, known for its popular surf beaches and relaxed seaside lifestyle.
  • B. Parramatta
    Parramatta is a major commercial and cultural centre in Western Sydney, Australia, known for its historic sites, diverse community, and role as a secondary CBD of the Sydney metropolitan area.
  • C. Tweed Heads
    Tweed Heads is a coastal town in far northeastern New South Wales, Australia, situated on the Tweed River near the Queensland border and known for its beaches and tourism.
  • D. Kirrawee
    Kirrawee is a suburban residential and commercial area in southern Sydney, New South Wales, Australia.
  • E. Emu Heights
    Emu Heights is a residential suburb within the coastal city of Burnie in north-west Tasmania, Australia.
  • 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_69e0c46d3284819099a4f9d5a704eb95 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69effd064fcc819084852b4248f65a81 completed April 28, 2026, 12:19 a.m.
Created at: April 16, 2026, 6:48 p.m.