Triple

T17447738
Position Surface form Disambiguated ID Type / Status
Subject Manas International Airport E424828 entity
Predicate ICAOcode P419 FINISHED
Object UCFM
UCFM is the ICAO airport code for Manas International Airport, the main international airport serving Bishkek, Kyrgyzstan.
E1269294 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: UCFM | Statement: [Manas International Airport, ICAOcode, UCFM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UCFM
Context triple: [Manas International Airport, ICAOcode, UCFM]
  • A. UFM
    UFM is a private Guatemalan university known for its strong emphasis on classical liberalism, free-market economics, and individual liberty.
  • B. UCFC
    UCFC is the commonly used abbreviation for Utica City FC, a professional indoor soccer club based in Utica, New York.
  • C. CUFLA
    CUFLA is a student-run organization at Carleton University dedicated to promoting and organizing competitive and recreational ultimate frisbee activities.
  • D. CFU
    CFU is the commonly used abbreviation for the Caribbean Football Union, the governing body for association football in the Caribbean region.
  • E. CFU
    CFU is the IATA airport code for Corfu International Airport, the main air gateway to the Greek island of Corfu.
  • 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: UCFM
Triple: [Manas International Airport, ICAOcode, UCFM]
Generated description
UCFM is the ICAO airport code for Manas International Airport, the main international airport serving Bishkek, Kyrgyzstan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: UCFM
Target entity description: UCFM is the ICAO airport code for Manas International Airport, the main international airport serving Bishkek, Kyrgyzstan.
  • A. UFM
    UFM is a private Guatemalan university known for its strong emphasis on classical liberalism, free-market economics, and individual liberty.
  • B. UCFC
    UCFC is the commonly used abbreviation for Utica City FC, a professional indoor soccer club based in Utica, New York.
  • C. CUFLA
    CUFLA is a student-run organization at Carleton University dedicated to promoting and organizing competitive and recreational ultimate frisbee activities.
  • D. CFU
    CFU is the commonly used abbreviation for the Caribbean Football Union, the governing body for association football in the Caribbean region.
  • E. CFU
    CFU is a municipal utility provider serving the Cedar Falls, Iowa area with services such as electricity, water, natural gas, and communications.
  • 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_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44ffe18f08190be023de89e3d7d5c completed April 19, 2026, 3:46 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01affab32081908d97960513a6e8e4 completed May 11, 2026, 10:31 a.m.
NEDg Description generation batch_6a01b164864481909673d9351bb7f817 completed May 11, 2026, 10:37 a.m.
NED2 Entity disambiguation (via description) batch_6a01b251040c8190a1d030cb55e4f052 completed May 11, 2026, 10:41 a.m.
Created at: April 10, 2026, 5:47 a.m.