Triple
T10871699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exuma International Airport |
E256668
|
entity |
| Predicate | pushpinLabel |
P9248
|
FINISHED |
| Object | GGT |
E889965
|
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: GGT | Statement: [Exuma International Airport, pushpinLabel, GGT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GGT Context triple: [Exuma International Airport, pushpinLabel, GGT]
-
A.
GGT
chosen
GGT is the IATA airport code for Exuma International Airport, which serves Great Exuma in The Bahamas.
-
B.
MGGT
MGGT is the ICAO airport code for La Aurora International Airport, the main international gateway serving Guatemala City, Guatemala.
-
C.
TGG
TGG is the IATA airport code for Sultan Mahmud Airport, which serves Kuala Terengganu in Malaysia.
-
D.
GBTT
GBTT is the historic radio call sign assigned to the British ocean liner RMS Queen Mary.
-
E.
GG
GG was the original designation for New York City's G subway service, a crosstown line that runs through Brooklyn and Queens without entering Manhattan.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75186e75c8190bf046ea666faff54 |
completed | April 9, 2026, 7:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e154cc97f88190aef41d18b5ebe836 |
completed | April 16, 2026, 9:29 p.m. |
Created at: April 8, 2026, 9:21 p.m.