Triple
T12505833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Smith Regional Airport |
E298945
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | FSM |
E44662
|
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: FSM | Statement: [Fort Smith Regional Airport, IATAcode, FSM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FSM Context triple: [Fort Smith Regional Airport, IATAcode, FSM]
-
A.
FSM
FSM is the abbreviation for the French Submarine Forces, the branch of the French Navy responsible for operating and maintaining France’s submarine fleet, including its nuclear deterrent.
-
B.
FSM
chosen
FSM is the three-letter ISO 3166-1 alpha-3 country code for the Federated States of Micronesia, a Pacific island nation.
-
C.
GFSM
GFSM is the standard IMF framework for compiling and presenting comprehensive, internationally comparable statistics on government finances.
-
D.
FSMTC
FSMTC is the primary telecommunications provider in the Federated States of Micronesia, offering services such as telephone, internet, and mobile communications across the islands.
-
E.
DFA
DFA is an online advertising management and ad-serving platform originally developed by DoubleClick and later integrated into Google's marketing and ad technology stack.
- 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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94dfddf38819099263b8b1e804736 |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64bb5af708190b3786da334c3bf23 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 8, 2026, 9:57 p.m.