Triple

T3911665
Position Surface form Disambiguated ID Type / Status
Subject Kota Kinabalu International Airport E87334 entity
Predicate IATAcode P418 FINISHED
Object BKI
BKI is the IATA airport code for Kota Kinabalu International Airport, a major air gateway to the Malaysian state of Sabah on the island of Borneo.
 E398411 NE FINISHED

How this triple was built (4 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: BKI | Statement: [Kota Kinabalu International Airport, IATAcode, BKI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BKI
Context triple: [Kota Kinabalu International Airport, IATAcode, BKI]
  • A. BKL
    BKL is an alternative name for the Big Circle Line, a major circular metro line in Moscow’s rapid transit system.
  • B. BKL
    BKL is the FAA airport code for Burke Lakefront Airport, a public airport located on the shore of Lake Erie in Cleveland, Ohio.
  • C. BKR
    BKR is the postal code prefix used for addresses in the town of Birkirkara in Malta.
  • D. BKR
    BKR was the abbreviated name of the People's Security Agency, an early post-World War II Indonesian security and defense organization.
  • E. BK
    BK is a common abbreviation for Brooklyn, a borough of New York City known for its cultural diversity, arts scene, and historic neighborhoods.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: BKI
Triple: [Kota Kinabalu International Airport, IATAcode, BKI]
Generated description
BKI is the IATA airport code for Kota Kinabalu International Airport, a major air gateway to the Malaysian state of Sabah on the island of Borneo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BKI
Target entity description: BKI is the IATA airport code for Kota Kinabalu International Airport, a major air gateway to the Malaysian state of Sabah on the island of Borneo.
  • A. BKL
    BKL is an alternative name for the Big Circle Line, a major circular metro line in Moscow’s rapid transit system.
  • B. BKL
    BKL is the FAA airport code for Burke Lakefront Airport, a public airport located on the shore of Lake Erie in Cleveland, Ohio.
  • C. BKR
    BKR was the abbreviated name of the People's Security Agency, an early post-World War II Indonesian security and defense organization.
  • D. BKR
    BKR is the postal code prefix used for addresses in the town of Birkirkara in Malta.
  • E. BK
    BK is a common abbreviation for Brooklyn, a borough of New York City known for its cultural diversity, arts scene, and historic neighborhoods.
  • F. None of above. chosen

Provenance (5 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_69aed9424514819086e9c58adde6652d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed35e2d081908b5d87c7630e7ffc completed March 9, 2026, 3:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51cb454c48190bf47d080f6cc24f0 completed March 14, 2026, 8:30 a.m.
NEDg Description generation batch_69b5206dfd848190ae7aaa9997150934 completed March 14, 2026, 8:46 a.m.
NED2 Entity disambiguation (via description) batch_69b520ce6af481909b7824c2ec221331 completed March 14, 2026, 8:48 a.m.
Created at: March 9, 2026, 3:22 p.m.