Triple
T18627945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foz do Iguaçu International Airport |
E455332
|
entity |
| Predicate | IATA code |
P2569
|
FINISHED |
| Object | IGU |
—
|
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: IGU | Statement: [Foz do Iguaçu International Airport, IATA code, IGU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IGU Context triple: [Foz do Iguaçu International Airport, IATA code, IGU]
-
A.
IGU
chosen
IGU is the IATA airport code for Foz do Iguaçu International Airport in Brazil, serving the Iguaçu Falls region.
-
B.
IGR
IGR is the IATA airport code for Cataratas del Iguazú International Airport serving Puerto Iguazú in Argentina, a gateway to the Iguazú Falls.
-
C.
IUG
IUG is an acronym commonly used to refer to the Islamic University of Gaza, a major higher education institution in the Gaza Strip.
-
D.
IGAS
IGAS is an organization focused on advancing interdisciplinary collaboration and innovation across the global arts and sciences communities.
-
E.
IGS
IGS is the IATA airport code assigned to Neuburg Air Base in Germany.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f063a1c819087e544c64f5cf80f |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.