Triple

T14033123
Position Surface form Disambiguated ID Type / Status
Subject Academia da Força Aérea E337641 entity
Predicate shortName P43 FINISHED
Object AFA
AFA is the commonly used abbreviation for Academia da Força Aérea, the Brazilian Air Force Academy responsible for training future Air Force officers.
 E1075022 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: AFA | Statement: [Academia da Força Aérea, shortName, AFA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AFA
Context triple: [Academia da Força Aérea, shortName, AFA]
  • A. AFA
    AFA is the IATA airport code for San Rafael's main airport in Mendoza Province, Argentina.
  • B. AFA
    AFA is the Argentine Football Association, the main governing body responsible for organizing and regulating football in Argentina, including its national teams and professional leagues.
  • C. AfA
    AfA is the abbreviation for the Arbeitsgemeinschaft für Arbeitnehmerfragen, a labor-oriented working group within Germany’s Social Democratic Party (SPD) that represents employees’ interests.
  • D. AFAC
    AFAC is Mexico’s Federal Civil Aviation Agency responsible for regulating and overseeing civil aviation activities in the country.
  • 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: AFA
Triple: [Academia da Força Aérea, shortName, AFA]
Generated description
AFA is the commonly used abbreviation for Academia da Força Aérea, the Brazilian Air Force Academy responsible for training future Air Force officers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AFA
Target entity description: AFA is the commonly used abbreviation for Academia da Força Aérea, the Brazilian Air Force Academy responsible for training future Air Force officers.
  • A. AFA
    AFA is the Argentine Football Association, the main governing body responsible for organizing and regulating football in Argentina, including its national teams and professional leagues.
  • B. AFA
    AFA is the IATA airport code for San Rafael's main airport in Mendoza Province, Argentina.
  • C. AfA
    AfA is the abbreviation for the Arbeitsgemeinschaft für Arbeitnehmerfragen, a labor-oriented working group within Germany’s Social Democratic Party (SPD) that represents employees’ interests.
  • D. AFAC
    AFAC is Mexico’s Federal Civil Aviation Agency responsible for regulating and overseeing civil aviation activities in the country.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2fab17008190981f1808726fa11c completed April 14, 2026, 12:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc337a5cc8190953b84255a401ada completed May 6, 2026, 10:39 p.m.
NEDg Description generation batch_69fbc558d980819080c64df19907b4ec completed May 6, 2026, 10:48 p.m.
NED2 Entity disambiguation (via description) batch_69fbc5d76cdc8190970778580437cf72 completed May 6, 2026, 10:51 p.m.
Created at: April 9, 2026, 10:20 p.m.