Triple
T20685676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WADD |
E508408
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | Angkasa Pura I |
—
|
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: Angkasa Pura I | Statement: [WADD, operator, Angkasa Pura I]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angkasa Pura I Context triple: [WADD, operator, Angkasa Pura I]
-
A.
Angkasa Pura I
chosen
Angkasa Pura I is an Indonesian state-owned enterprise that manages and operates numerous major airports across central and eastern Indonesia.
-
B.
Angkasa Pura II
Angkasa Pura II is an Indonesian state-owned enterprise that manages and operates numerous major airports across western Indonesia.
-
C.
Adisutjipto International Airport
Adisutjipto International Airport is the main commercial airport serving the Yogyakarta region on the island of Java, Indonesia.
-
D.
Husein Sastranegara International Airport
Husein Sastranegara International Airport is the main commercial airport serving the city of Bandung in West Java, Indonesia.
-
E.
Halim Perdanakusuma International Airport
Halim Perdanakusuma International Airport is a major airport in Jakarta, Indonesia, serving both commercial flights and military operations.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beabf72881909771b6c6a81276d6 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 11:45 a.m.