Triple

T4749888
Position Surface form Disambiguated ID Type / Status
Subject Gimpo International Airport E105451 entity
Predicate connectedBy P37 FINISHED
Object AREX
AREX is a South Korean airport railroad line that provides rapid rail transit between central Seoul and its major airports, including Gimpo and Incheon.
E467931 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: AREX | Statement: [Gimpo International Airport, connectedBy, AREX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AREX
Context triple: [Gimpo International Airport, connectedBy, AREX]
  • A. REX
    REX is a radio science experiment instrument aboard NASA's New Horizons spacecraft used to study the atmospheres and surfaces of planetary bodies through radio signal measurements.
  • B. AKX
    AKX is the IATA airport code for Aktobe International Airport in Aktobe, Kazakhstan.
  • C. ARCX
    ARCX is the Market Identifier Code for the NYSE Arca exchange, an electronic securities trading platform operated by the New York Stock Exchange.
  • D. Arcop
    Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
  • E. AXS
    AXS is a digital ticketing and event management platform known for selling and distributing tickets for sports, concerts, and live entertainment events.
  • 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: AREX
Triple: [Gimpo International Airport, connectedBy, AREX]
Generated description
AREX is a South Korean airport railroad line that provides rapid rail transit between central Seoul and its major airports, including Gimpo and Incheon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AREX
Target entity description: AREX is a South Korean airport railroad line that provides rapid rail transit between central Seoul and its major airports, including Gimpo and Incheon.
  • A. REX
    REX is a radio science experiment instrument aboard NASA's New Horizons spacecraft used to study the atmospheres and surfaces of planetary bodies through radio signal measurements.
  • B. AKX
    AKX is the IATA airport code for Aktobe International Airport in Aktobe, Kazakhstan.
  • C. ARCX
    ARCX is the Market Identifier Code for the NYSE Arca exchange, an electronic securities trading platform operated by the New York Stock Exchange.
  • D. Arcop
    Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
  • E. AXS
    AXS is a digital ticketing and event management platform known for selling and distributing tickets for sports, concerts, and live entertainment events.
  • 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_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.
Created at: March 20, 2026, 1:20 p.m.