Triple
T22356518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Force Academy |
E552664
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | AFA |
—
|
NE NERFINISHED |
How this triple was built (2 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: [Air Force Academy, abbreviation, AFA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AFA Context triple: [Air Force Academy, abbreviation, AFA]
-
A.
AFA
AFA is the IATA airport code for San Rafael's main airport in Mendoza Province, Argentina.
-
B.
AFA
AFA is an abbreviation commonly used for the ARY Film Awards, a Pakistani awards ceremony honoring achievements in the film industry.
-
C.
AFA
chosen
AFA is the commonly used abbreviation for Academia da Força Aérea, the Brazilian Air Force Academy responsible for training future Air Force officers.
-
D.
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.
-
E.
AFAA
AFAA is the organization responsible for organizing and presenting the Asian Film Awards, which honor excellence in Asian cinema.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157d08b148190a9a4e445e8579219 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:44 p.m.