Triple

T19371201
Position Surface form Disambiguated ID Type / Status
Subject Ventspils International Airport E484539 entity
Predicate ICAOcode P419 FINISHED
Object EVVA
EVVA is the ICAO airport code for Ventspils International Airport in Latvia.
 E1372673 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: EVVA | Statement: [Ventspils International Airport, ICAOcode, EVVA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EVVA
Context triple: [Ventspils International Airport, ICAOcode, EVVA]
  • A. EGVA
    EGVA is the ICAO airport code for RAF Fairford, a Royal Air Force station in Gloucestershire, England used primarily by the United States Air Force for bomber and airlift operations.
  • B. EVA
    EVA is the ICAO airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
  • C. Novaggio
    Novaggio is a small municipality in the canton of Ticino in southern Switzerland, known for its scenic hillside setting above Lake Lugano.
  • D. EAEVE
    EAEVE is a European organization that evaluates and accredits veterinary education institutions to ensure high standards of veterinary training across Europe.
  • E. VeRa
    VeRa is a radio science experiment on the Venus Express spacecraft designed to study Venus’s atmosphere, ionosphere, and gravity field using radio occultation and tracking techniques.
  • 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: EVVA
Triple: [Ventspils International Airport, ICAOcode, EVVA]
Generated description
EVVA is the ICAO airport code for Ventspils International Airport in Latvia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EVVA
Target entity description: EVVA is the ICAO airport code for Ventspils International Airport in Latvia.
  • A. EGVA
    EGVA is the ICAO airport code for RAF Fairford, a Royal Air Force station in Gloucestershire, England used primarily by the United States Air Force for bomber and airlift operations.
  • B. EVA
    EVA is the ICAO airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
  • C. Novaggio
    Novaggio is a small municipality in the canton of Ticino in southern Switzerland, known for its scenic hillside setting above Lake Lugano.
  • D. EAEVE
    EAEVE is a European organization that evaluates and accredits veterinary education institutions to ensure high standards of veterinary training across Europe.
  • E. VeRa
    VeRa is a radio science experiment on the Venus Express spacecraft designed to study Venus’s atmosphere, ionosphere, and gravity field using radio occultation and tracking techniques.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619b09ef08190a8b420316c0b8eb3 completed April 20, 2026, 12:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a072419c4ec8190931c1918450f2a83 completed May 15, 2026, 1:48 p.m.
NEDg Description generation batch_6a0725c32c4c8190bb29a764695cd245 completed May 15, 2026, 1:55 p.m.
NED2 Entity disambiguation (via description) batch_6a0726ea260c8190b97e2b18fde36272 completed May 15, 2026, 2 p.m.
Created at: April 10, 2026, 1:35 p.m.