Triple

T15873573
Position Surface form Disambiguated ID Type / Status
Subject Paro Airport E384889 entity
Predicate ICAOcode P419 FINISHED
Object VQPR
VQPR is the ICAO airport code for Paro Airport, the primary international airport of Bhutan known for its challenging approach amid Himalayan terrain.
E1180943 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: VQPR | Statement: [Paro Airport, ICAOcode, VQPR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: VQPR
Context triple: [Paro Airport, ICAOcode, VQPR]
  • A. QVT
    QVT (Query/View/Transformation) is an OMG standard language for specifying model-to-model transformations in model-driven software engineering.
  • B. VVPQ
    VVPQ is the ICAO airport code assigned to Phu Quoc International Airport in Vietnam.
  • C. CYVQ
    CYVQ is the ICAO airport code for Norman Wells Airport, a regional air transport hub in the Northwest Territories of Canada.
  • D. QAVS
    QAVS is a prestigious UK national honour that recognises outstanding voluntary groups for their exceptional service to local communities.
  • E. QOR
    QOR is the abbreviation commonly used for The Queen's Own Rifles of Canada, a historic primary reserve infantry regiment of the Canadian Army.
  • 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: VQPR
Triple: [Paro Airport, ICAOcode, VQPR]
Generated description
VQPR is the ICAO airport code for Paro Airport, the primary international airport of Bhutan known for its challenging approach amid Himalayan terrain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: VQPR
Target entity description: VQPR is the ICAO airport code for Paro Airport, the primary international airport of Bhutan known for its challenging approach amid Himalayan terrain.
  • A. QVT
    QVT (Query/View/Transformation) is an OMG standard language for specifying model-to-model transformations in model-driven software engineering.
  • B. VVPQ
    VVPQ is the ICAO airport code assigned to Phu Quoc International Airport in Vietnam.
  • C. CYVQ
    CYVQ is the ICAO airport code for Norman Wells Airport, a regional air transport hub in the Northwest Territories of Canada.
  • D. QAVS
    QAVS is a prestigious UK national honour that recognises outstanding voluntary groups for their exceptional service to local communities.
  • E. QOR
    QOR is the abbreviation commonly used for The Queen's Own Rifles of Canada, a historic primary reserve infantry regiment of the Canadian Army.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fc02688190b6f070882b846516 completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa94e9b548190bec74e6d9790d241 completed May 9, 2026, 9:38 p.m.
NEDg Description generation batch_69ffaa07df788190bae67f3d9a800331 completed May 9, 2026, 9:41 p.m.
NED2 Entity disambiguation (via description) batch_69ffaaa92a648190a09829ef3197223c completed May 9, 2026, 9:44 p.m.
Created at: April 10, 2026, 4:51 a.m.