Triple

T5846792
Position Surface form Disambiguated ID Type / Status
Subject Korla E129730 entity
Predicate airport P1065 FINISHED
Object Korla Airport E553757 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: Korla Airport | Statement: [Korla, airport, Korla Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Korla Airport
Context triple: [Korla, airport, Korla Airport]
  • A. Korla Airport chosen
    Korla Airport is a regional civil airport serving the city of Korla in Xinjiang, China, providing both passenger and cargo air services.
  • B. Hotan Airport
    Hotan Airport is a regional civil airport serving the city of Hotan in Xinjiang, China, providing both passenger and limited cargo air services.
  • C. Urumqi Diwopu International Airport
    Urumqi Diwopu International Airport is a major international airport in Ürümqi, Xinjiang, serving as a key aviation gateway between China and Central Asia.
  • D. Andijan Airport
    Andijan Airport is a regional public airport serving the city of Andijan in eastern Uzbekistan, handling domestic flights and limited international services.
  • E. Zhuliany Airport
    Zhuliany Airport is a major international airport serving Kyiv, Ukraine, known for its proximity to the city center and focus on regional and low-cost flights.
  • 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_69c0084bd31c8190a796bb6284845e83 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0351157508190a78d2a7141e0cee8 completed March 22, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0bfd6cffc8190b65252f02055e89c completed March 23, 2026, 4:21 a.m.
Created at: March 22, 2026, 3:55 p.m.