Triple

T5535321
Position Surface form Disambiguated ID Type / Status
Subject Severo-Kurilsk Airport E145146 entity
Predicate IATACode P418 FINISHED
Object SWV
SWV is the IATA airport code for Severo-Kurilsk Airport, which serves the town of Severo-Kurilsk in Russia’s Kuril Islands.
 E527996 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: SWV | Statement: [Severo-Kurilsk Airport, IATACode, SWV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SWV
Context triple: [Severo-Kurilsk Airport, IATACode, SWV]
  • A. SWV
    SWV (Sisters With Voices) is an American R&B girl group best known for their 1990s hits like "Weak," "Right Here/Human Nature," and "I'm So Into You."
  • B. SWC
    SWC is the abbreviation for the Southwest Conference, a former NCAA Division I college athletic conference that primarily featured schools from Texas and the surrounding region.
  • C. SWC
    SWC is the acronym for the South Western Command of the Indian Army, a major operational command responsible for defense and military operations in India’s western sector.
  • D. SWA
    SWA is the National Rail station code for Swansea railway station, a major rail hub in Swansea, Wales.
  • E. SWA
    SWA is the ICAO airline designator used to identify Southwest Airlines in aviation operations and air traffic control.
  • 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: SWV
Triple: [Severo-Kurilsk Airport, IATACode, SWV]
Generated description
SWV is the IATA airport code for Severo-Kurilsk Airport, which serves the town of Severo-Kurilsk in Russia’s Kuril Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SWV
Target entity description: SWV is the IATA airport code for Severo-Kurilsk Airport, which serves the town of Severo-Kurilsk in Russia’s Kuril Islands.
  • A. SWV
    SWV (Sisters With Voices) is an American R&B girl group best known for their 1990s hits like "Weak," "Right Here/Human Nature," and "I'm So Into You."
  • B. SWC
    SWC is the abbreviation for the Southwest Conference, a former NCAA Division I college athletic conference that primarily featured schools from Texas and the surrounding region.
  • C. SWC
    SWC is the acronym for the South Western Command of the Indian Army, a major operational command responsible for defense and military operations in India’s western sector.
  • D. SWA
    SWA is the National Rail station code for Swansea railway station, a major rail hub in Swansea, Wales.
  • E. SWA
    SWA is the ICAO airline designator used to identify Southwest Airlines in aviation operations and air traffic control.
  • 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_69c008f9955881909bfa8348b56b4739 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01faed1d08190b6a57faedaf1b56a completed March 22, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c02810084c81909fde56d6ee4ad328 completed March 22, 2026, 5:34 p.m.
NEDg Description generation batch_69c033df2c7881909660eb931908318c completed March 22, 2026, 6:24 p.m.
NED2 Entity disambiguation (via description) batch_69c034640cd081909b44ff23e9005e57 completed March 22, 2026, 6:26 p.m.
Created at: March 22, 2026, 3:34 p.m.