Triple

T14020246
Position Surface form Disambiguated ID Type / Status
Subject Greater Melbourne E337310 entity
Predicate hasAirport P105 FINISHED
Object Melbourne Airport E30111 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: Melbourne Airport | Statement: [Greater Melbourne, hasAirport, Melbourne Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Melbourne Airport
Context triple: [Greater Melbourne, hasAirport, Melbourne Airport]
  • A. Melbourne Airport (Tullamarine) chosen
    Melbourne Airport (Tullamarine) is the primary international and domestic airport serving the city of Melbourne, Australia.
  • B. Griffith Airport
    Griffith Airport is a regional airport serving the city of Griffith and the surrounding Riverina area in New South Wales, 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. Melbourne Regional Airport
    Melbourne Regional Airport is a public airport in Melbourne, Florida, that serves as a commercial and general aviation gateway for the Space Coast region.
  • E. Adelaide Airport
    Adelaide Airport is the principal international and domestic airport serving the city of Adelaide and the state of South Australia.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2f3c7cd88190b236382058581740 completed April 14, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c229f448190b7ea1a1bf9d086cf completed May 8, 2026, 2:36 a.m.
Created at: April 9, 2026, 10:19 p.m.