Triple

T5718554
Position Surface form Disambiguated ID Type / Status
Subject Magadan Airport E126081 entity
Predicate hasIATAcode P2569 FINISHED
Object GDX
GDX is the IATA airport code for Magadan Airport, which serves the city of Magadan in Russia’s Far East.
 E541288 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: GDX | Statement: [Magadan Airport, hasIATAcode, GDX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GDX
Context triple: [Magadan Airport, hasIATAcode, GDX]
  • A. GDN
    GDN is the vehicle registration code assigned to motor vehicles registered in the Pomeranian Voivodeship of Poland.
  • B. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • C. GDF
    GDF is the Global Drug Facility, an international mechanism that supplies quality-assured medicines and diagnostics to support tuberculosis control and treatment programs worldwide.
  • D. DGS
    DGS is the California state agency that provides centralized business, procurement, real estate, and support services to other government departments.
  • E. DGS
    The DGS was the notorious political police force of Portugal’s Estado Novo dictatorship, responsible for repressing dissent and persecuting regime opponents.
  • 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: GDX
Triple: [Magadan Airport, hasIATAcode, GDX]
Generated description
GDX is the IATA airport code for Magadan Airport, which serves the city of Magadan in Russia’s Far East.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GDX
Target entity description: GDX is the IATA airport code for Magadan Airport, which serves the city of Magadan in Russia’s Far East.
  • A. GDN
    GDN is the vehicle registration code assigned to motor vehicles registered in the Pomeranian Voivodeship of Poland.
  • B. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • C. GDF
    GDF is the Global Drug Facility, an international mechanism that supplies quality-assured medicines and diagnostics to support tuberculosis control and treatment programs worldwide.
  • D. DGS
    The DGS was the notorious political police force of Portugal’s Estado Novo dictatorship, responsible for repressing dissent and persecuting regime opponents.
  • E. DGS
    DGS is the California state agency that provides centralized business, procurement, real estate, and support services to other government departments.
  • 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_69c0082e3d548190950169847b43043b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c024e084cc81909a652f7c10d32c32 completed March 22, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a7af5788190827ff8050eb6416d completed March 22, 2026, 9:09 p.m.
NEDg Description generation batch_69c05c75179c819085bf56340363b48c completed March 22, 2026, 9:17 p.m.
NED2 Entity disambiguation (via description) batch_69c05d2ef9488190ac0111cb6a94b1d0 completed March 22, 2026, 9:20 p.m.
Created at: March 22, 2026, 3:46 p.m.