Triple

T1494629
Position Surface form Disambiguated ID Type / Status
Subject Gimhae International Airport E29657 entity
Predicate hubFor P423 FINISHED
Object Air Busan
Air Busan is a South Korean low-cost airline based in Busan that operates domestic and international flights across East Asia.
 E170452 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: Air Busan | Statement: [Gimhae International Airport, hubFor, Air Busan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Air Busan
Context triple: [Gimhae International Airport, hubFor, Air Busan]
  • A. Airbus A380
    The Airbus A380 is a double-deck, wide-body, four-engine jet airliner that is the world's largest passenger aircraft, designed for long-haul, high-capacity flights.
  • B. Airbus Voyager
    Airbus Voyager is a military air-to-air refuelling and transport aircraft used primarily by the Royal Air Force, based on the Airbus A330 platform.
  • C. SPEEDBIRD
    SPEEDBIRD is the radio callsign used by British Airways for its commercial flight operations.
  • D. Airbus A350
    The Airbus A350 is a long-range, wide-body twin-engine jet airliner made largely of composite materials and designed to compete with the Boeing 787 and 777 in fuel-efficient long-haul travel.
  • E. Airbus Beluga
    The Airbus Beluga is a large, whale-shaped cargo aircraft designed for transporting oversized aerospace components and other outsize freight.
  • 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: Air Busan
Triple: [Gimhae International Airport, hubFor, Air Busan]
Generated description
Air Busan is a South Korean low-cost airline based in Busan that operates domestic and international flights across East Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Air Busan
Target entity description: Air Busan is a South Korean low-cost airline based in Busan that operates domestic and international flights across East Asia.
  • A. Airbus A380
    The Airbus A380 is a double-deck, wide-body, four-engine jet airliner that is the world's largest passenger aircraft, designed for long-haul, high-capacity flights.
  • B. Airbus Voyager
    Airbus Voyager is a military air-to-air refuelling and transport aircraft used primarily by the Royal Air Force, based on the Airbus A330 platform.
  • C. SPEEDBIRD
    SPEEDBIRD is the radio callsign used by British Airways for its commercial flight operations.
  • D. Airbus A350
    The Airbus A350 is a long-range, wide-body twin-engine jet airliner made largely of composite materials and designed to compete with the Boeing 787 and 777 in fuel-efficient long-haul travel.
  • E. Airbus Beluga
    The Airbus Beluga is a large, whale-shaped cargo aircraft designed for transporting oversized aerospace components and other outsize freight.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6c78c9481909b210b845aa6e9df completed March 1, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1cadb50481908788b5710f6012db completed March 8, 2026, 6:52 a.m.
NEDg Description generation batch_69ad1deb982481908f542c233c9352ab completed March 8, 2026, 6:57 a.m.
NED2 Entity disambiguation (via description) batch_69ad1e79aecc8190a4c7d0f30fdc7e63 completed March 8, 2026, 7 a.m.
Created at: March 1, 2026, 8:12 p.m.