Triple
T19262633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VAJB |
E481686
|
entity |
| Predicate | ICAOCodeFor |
P419
|
FINISHED |
| Object | Dumna Airport |
—
|
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: Dumna Airport | Statement: [VAJB, ICAOCodeFor, Dumna Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dumna Airport Context triple: [VAJB, ICAOCodeFor, Dumna Airport]
-
A.
Dumna Airport
chosen
Dumna Airport is a domestic airport serving the city of Jabalpur in the Indian state of Madhya Pradesh.
-
B.
Dumatubin Airport
Dumatubin Airport is a small regional airport serving the Kai Islands in Indonesia, providing domestic air connections to this remote archipelago.
-
C.
Kadala Airport
Kadala Airport is the main commercial airport serving the city of Chita in eastern Siberia, Russia.
-
D.
Gunbalanya Airport
Gunbalanya Airport is a small regional airfield serving the remote community of Gunbalanya (formerly Oenpelli) in the Northern Territory of Australia.
-
E.
Tugdan Airport
Tugdan Airport is a domestic airport serving Tablas Island in Romblon province in the Philippines.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb8ac1a8819094309db4a2e6b163 |
completed | April 20, 2026, 10:10 a.m. |
Created at: April 10, 2026, 1:28 p.m.