Triple
T18241223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Las Mercedes Airport |
E436815
|
entity |
| Predicate | ICAOCode |
P419
|
FINISHED |
| Object | MNMG |
—
|
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: MNMG | Statement: [Las Mercedes Airport, ICAOCode, MNMG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MNMG Context triple: [Las Mercedes Airport, ICAOCode, MNMG]
-
A.
MNMG
chosen
MNMG is the ICAO airport code for Augusto C. Sandino International Airport, the main international gateway serving Managua, Nicaragua.
-
B.
MGN
MGN is the FAA airport code for Harbor Springs Municipal Airport, a public-use airfield serving Harbor Springs, Michigan.
-
C.
MGNI
MGNI is the stock ticker symbol for Magnite, a leading independent sell-side advertising platform for digital media.
-
D.
MNH
MNH was a German company that played a key role in producing Panther tanks for the Wehrmacht during World War II.
-
E.
M&GN
M&GN was a historic joint railway in eastern England, formally known as the Midland and Great Northern Joint Railway, that connected the Midlands to the Norfolk coast.
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e287548190b666a990e5b168b0 |
completed | April 19, 2026, 3:42 p.m. |
Created at: April 10, 2026, 10:33 a.m.