Triple

T15825468
Position Surface form Disambiguated ID Type / Status
Subject Pilot Point, Alaska E383729 entity
Predicate servedBy P82 FINISHED
Object Pilot Point Airport E1182139 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: Pilot Point Airport | Statement: [Pilot Point, Alaska, servedBy, Pilot Point Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pilot Point Airport
Context triple: [Pilot Point, Alaska, servedBy, Pilot Point Airport]
  • A. Pilot Point Airport chosen
    Pilot Point Airport is a public airport serving the remote community of Pilot Point on the Alaska Peninsula, primarily supporting regional and bush air service.
  • B. Tipton Airport
    Tipton Airport is a public general aviation airport in Maryland that primarily serves local and regional air traffic for the surrounding Howard County area.
  • C. Burnet Municipal Airport
    Burnet Municipal Airport is a public general aviation airport serving the city of Burnet and surrounding areas in Burnet County, Texas.
  • D. Mount Pleasant Municipal Airport
    Mount Pleasant Municipal Airport is a public general-aviation airport serving the city of Mount Pleasant in central Michigan.
  • E. Oakey Airport
    Oakey Airport is a regional airfield in Queensland, Australia, primarily serving general aviation and military training operations.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e11e602e5481908baa71c3d9b2008f completed April 16, 2026, 5:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5997a988190b7965e42d283459a completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:49 a.m.