Triple

T6089746
Position Surface form Disambiguated ID Type / Status
Subject Townsville Airport E135731 entity
Predicate connectsTo P845 FINISHED
Object Sydney Airport E58759 NE FINISHED

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: Sydney Airport | Statement: [Townsville Airport, connectsTo, Sydney Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sydney Airport
Context triple: [Townsville Airport, connectsTo, Sydney Airport]
  • A. Griffith Airport
    Griffith Airport is a regional airport serving the city of Griffith and the surrounding Riverina area in New South Wales, Australia.
  • B. Melbourne Airport (Tullamarine)
    Melbourne Airport (Tullamarine) is the primary international and domestic airport serving the city of Melbourne, Australia.
  • C. Brisbane Airport
    Brisbane Airport is a major international and domestic airport in Queensland, Australia, serving Brisbane and acting as a key hub for several airlines.
  • D. Sydney Kingsford Smith Airport chosen
    Sydney Kingsford Smith Airport is the primary international and domestic airport serving Sydney, Australia, and one of the busiest airports in the country.
  • E. Gold Coast Airport
    Gold Coast Airport is a major international and domestic airport serving Australia’s Gold Coast region and parts of northern New South Wales.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c0087bcc788190b20f093d3a6c60ec completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057a862c88190912a913973c6b6fc completed March 22, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c12531d764819083e1bb37d8c81a6c completed March 23, 2026, 11:34 a.m.
Created at: March 22, 2026, 4:12 p.m.