Triple

T22737916
Position Surface form Disambiguated ID Type / Status
Subject Liepāja International Airport E562324 entity
Predicate ICAOcode P419 FINISHED
Object EVLA
EVLA is the ICAO airport code for Liepāja International Airport in Latvia.
 E1552662 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: EVLA | Statement: [Liepāja International Airport, ICAOcode, EVLA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EVLA
Context triple: [Liepāja International Airport, ICAOcode, EVLA]
  • A. EVLA
    EVLA is a major upgrade of the Karl G. Jansky Very Large Array radio telescope in New Mexico, enhancing its sensitivity, frequency coverage, and overall scientific capabilities for radio astronomy.
  • B. EALA
    EALA is the regional legislative body of the East African Community responsible for making laws and providing oversight for the bloc.
  • C. EVVA
    EVVA is the ICAO airport code for Ventspils International Airport in Latvia.
  • D. ELV
    ELV is a launch pad at the Guiana Space Centre in French Guiana used primarily for launching European Vega rockets.
  • E. EVRA
    EVRA is the ICAO airport code for Riga International Airport, the main international gateway to Latvia’s capital city.
  • 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: EVLA
Triple: [Liepāja International Airport, ICAOcode, EVLA]
Generated description
EVLA is the ICAO airport code for Liepāja International Airport in Latvia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EVLA
Target entity description: EVLA is the ICAO airport code for Liepāja International Airport in Latvia.
  • A. EVLA
    EVLA is a major upgrade of the Karl G. Jansky Very Large Array radio telescope in New Mexico, enhancing its sensitivity, frequency coverage, and overall scientific capabilities for radio astronomy.
  • B. EALA
    EALA is the regional legislative body of the East African Community responsible for making laws and providing oversight for the bloc.
  • C. EVVA
    EVVA is the ICAO airport code for Ventspils International Airport in Latvia.
  • D. ELV
    ELV is a launch pad at the Guiana Space Centre in French Guiana used primarily for launching European Vega rockets.
  • E. EVRA
    EVRA is the ICAO airport code for Riga International Airport, the main international gateway to Latvia’s capital city.
  • 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_69e245513a5c81908d5cb471b4fc429d completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179707fd081909aed9b2f62b9f842 completed April 29, 2026, 3:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fce978c81908b83f84dc1357c91 completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b937b20008190817512be3d48df39 completed May 18, 2026, 10:32 p.m.
NED2 Entity disambiguation (via description) batch_6a0b946320e0819097ef9c4638595dff completed May 18, 2026, 10:36 p.m.
Created at: April 17, 2026, 3:22 p.m.