Triple

T5130852
Position Surface form Disambiguated ID Type / Status
Subject Deadhorse, Alaska E115694 entity
Predicate servedBy P82 FINISHED
Object Deadhorse Airport E160049 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: Deadhorse Airport | Statement: [Deadhorse, Alaska, servedBy, Deadhorse Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deadhorse Airport
Context triple: [Deadhorse, Alaska, servedBy, Deadhorse Airport]
  • A. Deadhorse Airport chosen
    Deadhorse Airport is a remote public airport on Alaska’s North Slope that primarily supports oil field operations and access to the Prudhoe Bay area.
  • B. Lee Gilmer Memorial Airport
    Lee Gilmer Memorial Airport is a public general aviation airport serving the city of Gainesville in Hall County, Georgia.
  • C. Spriggs Payne Airport
    Spriggs Payne Airport is a domestic airport serving the city of Monrovia in Liberia.
  • D. Pangborn Memorial Airport
    Pangborn Memorial Airport is a regional public airport serving the Wenatchee area in central Washington State, providing commercial and general aviation services.
  • E. Jolly Grant Airport
    Jolly Grant Airport is a domestic airport serving the city of Dehradun and the surrounding region in the Indian state of Uttarakhand.
  • 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd782904788190b544540483915c0e completed March 20, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4c626a48190b2fd81b88b5a59cc completed March 21, 2026, 4:18 p.m.
Created at: March 20, 2026, 1:42 p.m.