Triple
T4195812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fairbanks International Airport |
E89150
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | FAI |
E420383
|
NE FINISHED |
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: FAI | Statement: [Fairbanks International Airport, FAAcode, FAI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FAI Context triple: [Fairbanks International Airport, FAAcode, FAI]
-
A.
FAI
chosen
FAI is the IATA airport code for Fairbanks International Airport, a major air transport hub serving Fairbanks and interior Alaska.
-
B.
AIRFA
AIRFA is a U.S. federal law enacted in 1978 to protect and preserve the traditional religious rights and cultural practices of American Indians, Alaska Natives, and Native Hawaiians.
-
C.
FIS
FIS (Fédération Internationale de Ski) is the international governing body for skiing and snowboarding, responsible for overseeing major competitions and setting rules across multiple snow sports disciplines.
-
D.
FIA
"FIA" is a popular Afrobeats song by Nigerian artist Davido, known for its catchy melody and themes of love and betrayal.
-
E.
FFA
FFA is the commonly used abbreviation for the Fédération Française d’Athlétisme, the governing body for athletics in France.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69aed9569a4481908b6c1fcec2a11e21 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af035e87148190a0f0bf48b813ffaa |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5961f0de081908e2b6bee1725b97e |
completed | March 14, 2026, 5:08 p.m. |
Created at: March 9, 2026, 3:46 p.m.