Triple

T20507571
Position Surface form Disambiguated ID Type / Status
Subject Malmstrom Air Force Base E503473 entity
Predicate hasIATACode P2569 FINISHED
Object GFA
GFA is the IATA airport code for the airfield serving Malmstrom Air Force Base in Montana, United States.
 E1434537 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: GFA | Statement: [Malmstrom Air Force Base, hasIATACode, GFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GFA
Context triple: [Malmstrom Air Force Base, hasIATACode, GFA]
  • A. GFA
    GFA is the governing body responsible for organizing and overseeing football activities and competitions in Ghana.
  • B. GFA
    GFA is the ICAO airline designator used for Gulf Air, the national carrier of Bahrain.
  • C. GAFI
    GAFI is the French acronym for the Financial Action Task Force, an intergovernmental body that sets global standards to combat money laundering, terrorist financing, and related financial crimes.
  • D. GAFRI
    GAFRI is a U.S.-based financial services company specializing in life insurance, annuities, and related retirement products.
  • E. KFA
    KFA is the commonly used abbreviation for the Korea Football Association, the governing body of football in South Korea.
  • 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: GFA
Triple: [Malmstrom Air Force Base, hasIATACode, GFA]
Generated description
GFA is the IATA airport code for the airfield serving Malmstrom Air Force Base in Montana, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GFA
Target entity description: GFA is the IATA airport code for the airfield serving Malmstrom Air Force Base in Montana, United States.
  • A. GFA
    GFA is the ICAO airline designator used for Gulf Air, the national carrier of Bahrain.
  • B. GFA
    GFA is the governing body responsible for organizing and overseeing football activities and competitions in Ghana.
  • C. GAFI
    GAFI is the French acronym for the Financial Action Task Force, an intergovernmental body that sets global standards to combat money laundering, terrorist financing, and related financial crimes.
  • D. GAFRI
    GAFRI is a U.S.-based financial services company specializing in life insurance, annuities, and related retirement products.
  • E. KFA
    KFA is the commonly used abbreviation for the Korea Football Association, the governing body of football in South Korea.
  • 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_69e0b4b1e52c8190894281cf7e3283ab completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69dc8f3c881908ed2e0257a057e73 completed April 20, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0893c3839c8190aa20c6644a089a0b completed May 16, 2026, 3:56 p.m.
NEDg Description generation batch_6a089557444c819080d70a64596900f5 completed May 16, 2026, 4:03 p.m.
NED2 Entity disambiguation (via description) batch_6a0895de2b04819096246c63c3db5513 completed May 16, 2026, 4:05 p.m.
Created at: April 16, 2026, 11:36 a.m.