Triple
T23078731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sierra Vista Municipal Airport |
E575406
|
entity |
| Predicate | ICAOCode |
P419
|
FINISHED |
| Object | KFHU |
—
|
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: KFHU | Statement: [Sierra Vista Municipal Airport, ICAOCode, KFHU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KFHU Context triple: [Sierra Vista Municipal Airport, ICAOCode, KFHU]
-
A.
KFHU
chosen
KFHU is the ICAO airport code for Libby Army Airfield, a U.S. military airfield located at Fort Huachuca in Arizona.
-
B.
KFU
KFU is a major Russian research and educational institution officially known as Kazan (Volga Region) Federal University.
-
C.
KFHB
KFHB is the ICAO airport code for Fernandina Beach Municipal Airport, a public airport serving Fernandina Beach in northeastern Florida, United States.
-
D.
KHUF
KHUF is the ICAO airport code for Terre Haute Regional Airport, a public airport serving Terre Haute, Indiana, in the United States.
-
E.
FHU
FHU is the IATA airport code for Libby Army Airfield, a joint-use military and civilian airport serving the Fort Huachuca area in Arizona, United States.
- 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c6572d88190afab0dfa960a85dd |
completed | April 29, 2026, 4:43 a.m. |
Created at: April 17, 2026, 3:56 p.m.