Triple
T22454882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan Hasanuddin International Airport |
E555089
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | WAAA |
—
|
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: WAAA | Statement: [Sultan Hasanuddin International Airport, hasICAOCode, WAAA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WAAA Context triple: [Sultan Hasanuddin International Airport, hasICAOCode, WAAA]
-
A.
WAAA
chosen
WAAA is the ICAO airport code for Sultan Hasanuddin International Airport, the main air gateway to Makassar in South Sulawesi, Indonesia.
-
B.
WAA
WAA is the acronym for the Winnipeg Airports Authority, the organization responsible for operating and managing Winnipeg’s airport facilities.
-
C.
WAE
WAE is the IATA airport code for Wadi ad-Dawasir Domestic Airport serving the town of Wadi ad-Dawasir in Saudi Arabia.
-
D.
WAE
WAE is the National Rail station code for Waterloo East railway station in London, England.
-
E.
WAWA
WAWA is the station code for Wawa railway station, a train stop located in Wawa, New South Wales, Australia.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b4e2bd4819083e5bed44e9776c6 |
completed | April 29, 2026, 1:13 a.m. |
Created at: April 16, 2026, 8:48 p.m.