Triple

T23329997
Position Surface form Disambiguated ID Type / Status
Subject Woodbourne Airport E591417 entity
Predicate usedBy P260 FINISHED
Object Sounds Air 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: Sounds Air | Statement: [Woodbourne Airport, usedBy, Sounds Air]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sounds Air
Context triple: [Woodbourne Airport, usedBy, Sounds Air]
  • A. Sounds Air chosen
    Sounds Air is a New Zealand regional airline that operates short-haul domestic flights, particularly connecting smaller centers with major hubs.
  • B. Sounds
    Sounds was the short name of the Memphis Sounds, a former professional basketball team in the American Basketball Association (ABA) during the 1970s.
  • C. Soundgasm
    Soundgasm is a popular Afrobeats song by Nigerian artist Rema, known for its sensual lyrics and smooth, melodic production.
  • D. Atomic Sound
    Atomic Sound is a recording studio known for producing and engineering music projects such as those by the band Pollinator.
  • E. Back Sound
    Back Sound is a coastal waterway in North Carolina, United States, forming part of the chain of shallow sounds and inlets that separate the Outer Banks from the mainland.
  • 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f197ece360819099da8443dd86a355 completed April 29, 2026, 5:32 a.m.
Created at: April 17, 2026, 5:15 p.m.