Triple
T20545488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Tontouta International Airport |
E504458
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object | NSTU |
—
|
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: NSTU | Statement: [La Tontouta International Airport, ICAOcode, NSTU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NSTU Context triple: [La Tontouta International Airport, ICAOcode, NSTU]
-
A.
NSTU
chosen
NSTU is the ICAO airport code for Pago Pago International Airport in American Samoa.
-
B.
NSTU
NSTU is the commonly used abbreviation for Novosibirsk State Technical University, a major technical higher education institution in Novosibirsk, Russia.
-
C.
NSUT
NSUT is a premier engineering and technology university in New Delhi, India, known for its rigorous academics and strong research and innovation culture.
-
D.
NSU
NSU is a private research university in Fort Lauderdale, Florida, known for its programs in health professions, law, business, and education.
-
E.
NSU
NSU is a leading Russian research university located in Novosibirsk, known for its strong programs in science, technology, and mathematics.
- 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_69e0b4b52c048190952b4d0f430813a3 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a29684648190969d8fc23743e288 |
completed | April 20, 2026, 10:03 p.m. |
Created at: April 16, 2026, 11:38 a.m.