Triple
T7227461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yogyakarta International Airport |
E154816
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | WIRK |
E620555
|
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: WIRK | Statement: [Yogyakarta International Airport, ICAO code, WIRK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WIRK Context triple: [Yogyakarta International Airport, ICAO code, WIRK]
-
A.
WIRK
chosen
WIRK is the ICAO airport code assigned to Yogyakarta International Airport in Indonesia.
-
B.
WIT
WIT is the New York Stock Exchange ticker symbol for Wipro Limited, a major Indian multinational information technology services and consulting company.
-
C.
WINK
WINK is a type of regional multiple-unit train developed and marketed by Stadler Rail for efficient, flexible passenger service.
-
D.
WIL
WIL is the standard abbreviation used for the Wilmington Blue Rocks minor league baseball team.
-
E.
WIL
WIL is the IATA airport code for Wilson Airport, a busy domestic and regional airport serving Nairobi, Kenya.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6e9df72cc81908d1c04e6e310fbb4 |
completed | March 27, 2026, 8:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cc17a3788190842a852fb4b96185 |
completed | March 28, 2026, 12:39 p.m. |
Created at: March 27, 2026, 2:54 p.m.