Triple

T4749857
Position Surface form Disambiguated ID Type / Status
Subject Gimpo International Airport E105451 entity
Predicate formerIATAcode P58542 FINISHED
Object SEL
SEL is the former IATA airport code that once designated Seoul’s main international airport before it was replaced by newer facilities.
E467927 NE FINISHED

How this triple was built (5 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: SEL | Statement: [Gimpo International Airport, formerIATAcode, SEL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SEL
Context triple: [Gimpo International Airport, formerIATAcode, SEL]
  • A. SEN
    SEN is the three-letter IATA airport code for London Southend Airport in the United Kingdom.
  • B. Sel
    Sel is a municipality in Innlandet county, Norway, known for its mountainous landscapes and location in the Gudbrandsdalen valley.
  • C. SED
    SED was the ruling Marxist–Leninist party that governed East Germany (the German Democratic Republic) from its founding in 1949 until the end of communist rule in 1989.
  • D. SES
    SES is the commonly used abbreviation for St Edward's School, a co-educational independent boarding and day school in Oxford, England.
  • E. SE
    SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
  • 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: SEL
Triple: [Gimpo International Airport, formerIATAcode, SEL]
Generated description
SEL is the former IATA airport code that once designated Seoul’s main international airport before it was replaced by newer facilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SEL
Target entity description: SEL is the former IATA airport code that once designated Seoul’s main international airport before it was replaced by newer facilities.
  • A. SEN
    SEN is the three-letter IATA airport code for London Southend Airport in the United Kingdom.
  • B. Sel
    Sel is a municipality in Innlandet county, Norway, known for its mountainous landscapes and location in the Gudbrandsdalen valley.
  • C. SED
    SED was the ruling Marxist–Leninist party that governed East Germany (the German Democratic Republic) from its founding in 1949 until the end of communist rule in 1989.
  • D. SES
    SES is the commonly used abbreviation for St Edward's School, a co-educational independent boarding and day school in Oxford, England.
  • E. SE
    SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerIATAcode
Context triple: [Gimpo International Airport, formerIATAcode, SEL]
  • A. previousICAOcode
    Indicates that one entity was the former ICAO (International Civil Aviation Organization) code previously assigned to the other entity.
  • B. IATAcode
    Indicates the three-letter IATA airport or airline code assigned to the entity.
  • C. hasIATAcode
    Indicates that an entity, typically a transportation facility like an airport, is associated with a specific IATA (International Air Transport Association) code.
  • D. hasFormerAirport
    Indicates that an entity previously had an airport that is no longer in operation or no longer exists.
  • E. ICAOcode
    Indicates that an entity is identified by a specific four-letter airport or aerodrome code assigned by the International Civil Aviation Organization (ICAO).
  • F. None of above. chosen

Provenance (7 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_69bd43f07fa48190954317d01600994a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64c83af48190bd57be79c1505e9d completed March 20, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a4e0844819098bb9abb05094a89 completed March 21, 2026, 6:27 a.m.
NEDg Description generation batch_69be3c9f8e048190a951b26c36cb7b23 completed March 21, 2026, 6:37 a.m.
NED2 Entity disambiguation (via description) batch_69be3d232b888190a0fd64c55a18eb48 completed March 21, 2026, 6:39 a.m.
PD Predicate disambiguation batch_69bd6223defc8190823665a6592c1154 completed March 20, 2026, 3:05 p.m.
PDg Predicate description generation batch_69bd6424a1d08190ac1d5fc574dc1b55 completed March 20, 2026, 3:13 p.m.
Created at: March 20, 2026, 1:20 p.m.