Triple
T12746843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meridian Regional Airport |
E304626
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | MEI |
E999166
|
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: MEI | Statement: [Meridian Regional Airport, FAAcode, MEI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MEI Context triple: [Meridian Regional Airport, FAAcode, MEI]
-
A.
MEI
MEI is a climate index that quantifies the strength and phase of the El Niño–Southern Oscillation by combining multiple atmospheric and oceanic variables over the tropical Pacific.
-
B.
MEI
MEI is the vehicle registration code for the German town of Meissen in the state of Saxony.
-
C.
MEI
chosen
MEI is the three-letter IATA airport code for Meridian Regional Airport in Meridian, Mississippi, United States.
-
D.
MEI
MEI is an abbreviation for Matsushita Electric Industrial Co., the Japanese electronics company better known globally by its Panasonic brand.
-
E.
MEEI
MEEI is a renowned specialty hospital in Boston focused on ophthalmology and otolaryngology, affiliated with Harvard Medical School.
- 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_69d7bdf1426c8190a4402e1c4cdec33a |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96bd58d30819082af4edb4cd0b4ab |
completed | April 10, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684ee2ab4819099194d115d2e5a15 |
completed | May 2, 2026, 11:12 p.m. |
Created at: April 9, 2026, 5:27 p.m.