Triple

T11014861
Position Surface form Disambiguated ID Type / Status
Subject Khost E260337 entity
Predicate airportType P424 FINISHED
Object Khost Airport E900147 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: Khost Airport | Statement: [Khost, airportType, Khost Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khost Airport
Context triple: [Khost, airportType, Khost Airport]
  • A. Khost Airport chosen
    Khost Airport is a regional airport in Khost Province, Afghanistan, serving as a key hub for domestic air travel and connectivity in the southeastern part of the country.
  • B. Jalalabad Airport
    Jalalabad Airport is a regional airport in eastern Afghanistan that serves the city of Jalalabad and surrounding areas for both civilian and military aviation.
  • C. Bamyan Airport
    Bamyan Airport is a small regional airfield in central Afghanistan that serves the city of Bamyan and provides access to the surrounding mountainous province.
  • D. Kandahar International Airport
    Kandahar International Airport is a major airport in southern Afghanistan that serves both civilian flights and military operations.
  • E. Skardu International Airport
    Skardu International Airport is a key airport in Gilgit-Baltistan, Pakistan, serving as the main air gateway for tourists and locals traveling to the mountainous Skardu region and nearby Karakoram and Himalayan ranges.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797a49f648190a5144625d09dec6f completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c828b7848190be34a6ba1550d3f1 completed April 18, 2026, 6:06 p.m.
Created at: April 8, 2026, 9:25 p.m.