Triple

T12531855
Position Surface form Disambiguated ID Type / Status
Subject Thessaloniki Airport Makedonia E299587 entity
Predicate IATAcode P418 FINISHED
Object SKG
SKG is the three-letter IATA airport code for Thessaloniki Airport Makedonia in Greece.
 E988439 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: SKG | Statement: [Thessaloniki Airport Makedonia, IATAcode, SKG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SKG
Context triple: [Thessaloniki Airport Makedonia, IATAcode, SKG]
  • A. Skagen
    Skagen is a minimalist Danish-inspired watch and accessories brand known for its clean design aesthetic and modern, affordable timepieces.
  • B. Skagen
    Skagen is Denmark’s northernmost town, renowned for its picturesque fishing harbor, distinctive yellow houses, and the scenic meeting point of the North Sea and Baltic Sea.
  • C. SKW
    SKW is Poland’s Military Counterintelligence Service, responsible for protecting the armed forces and state defense structures from espionage, terrorism, and other security threats.
  • D. SKW
    SKW is the ICAO airline designator used to identify SkyWest Airlines in aviation operations and communications.
  • E. SKN
    SKN is the station code for South Kensington tube station, a major London Underground interchange serving the South Kensington area.
  • 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: SKG
Triple: [Thessaloniki Airport Makedonia, IATAcode, SKG]
Generated description
SKG is the three-letter IATA airport code for Thessaloniki Airport Makedonia in Greece.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SKG
Target entity description: SKG is the three-letter IATA airport code for Thessaloniki Airport Makedonia in Greece.
  • A. Skagen
    Skagen is a minimalist Danish-inspired watch and accessories brand known for its clean design aesthetic and modern, affordable timepieces.
  • B. Skagen
    Skagen is Denmark’s northernmost town, renowned for its picturesque fishing harbor, distinctive yellow houses, and the scenic meeting point of the North Sea and Baltic Sea.
  • C. SKW
    SKW is Poland’s Military Counterintelligence Service, responsible for protecting the armed forces and state defense structures from espionage, terrorism, and other security threats.
  • D. SKW
    SKW is the ICAO airline designator used to identify SkyWest Airlines in aviation operations and communications.
  • E. SKN
    SKN is the station code for South Kensington tube station, a major London Underground interchange serving the South Kensington area.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95469d100819087c83bc55e3ec9ce completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc8866c81908821525b595715e2 completed May 2, 2026, 7:08 p.m.
NEDg Description generation batch_69f64da25bf88190889273bf41e2f154 completed May 2, 2026, 7:16 p.m.
NED2 Entity disambiguation (via description) batch_69f65213ed84819086fda178aaf9e774 completed May 2, 2026, 7:35 p.m.
Created at: April 8, 2026, 9:57 p.m.