Triple
T3453675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kandahar |
E72850
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Kandahar International Airport |
E359353
|
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: Kandahar International Airport | Statement: [Kandahar, hasLandmark, Kandahar International Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kandahar International Airport Context triple: [Kandahar, hasLandmark, Kandahar International Airport]
-
A.
Kandahar International Airport
chosen
Kandahar International Airport is a major airport in southern Afghanistan that serves both civilian flights and military operations.
-
B.
Hamid Karzai International Airport
Hamid Karzai International Airport is the main international airport serving Kabul and the primary air gateway to Afghanistan.
-
C.
Dalbandin Airport
Dalbandin Airport is a small domestic airport serving the town of Dalbandin in Balochistan, Pakistan, providing regional air connectivity.
-
D.
Shah Makhdum Airport
Shah Makhdum Airport is a regional domestic airport serving the city of Rajshahi in western Bangladesh.
-
E.
Quetta International Airport
Quetta International Airport is the main domestic and international air gateway serving the city of Quetta and the surrounding region of Balochistan, Pakistan.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa457fc8190824ca00254e962f9 |
completed | March 8, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b373a7da208190a8a9ad5ede8d4f0f |
completed | March 13, 2026, 2:17 a.m. |
Created at: March 8, 2026, 3:16 p.m.