Triple
T17562023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Venezuelan Air Force |
E427713
|
entity |
| Predicate | usesAircraftModel |
P1524
|
FINISHED |
| Object | K-8 Karakorum |
—
|
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: K-8 Karakorum | Statement: [Venezuelan Air Force, usesAircraftModel, K-8 Karakorum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K-8 Karakorum Context triple: [Venezuelan Air Force, usesAircraftModel, K-8 Karakorum]
-
A.
K-8E Karakorum
chosen
The K-8E Karakorum is a Chinese-Pakistani jointly developed jet trainer aircraft variant used primarily for pilot training and light attack roles.
-
B.
Tujin
Tujin are a subgroup of the Sanhaja, a historic Berber confederation of North and Northwest Africa.
-
C.
Landi Kotal
Landi Kotal is a town in Pakistan’s Khyber District, historically significant as a key trading and military post near the Khyber Pass on the route to Afghanistan.
-
D.
Shergarh
Shergarh is a town in the Jodhpur district of Rajasthan, India, known for its rural setting and local administrative significance.
-
E.
Shergarh
Shergarh is the inner fortification within Pakistan’s historic Ranikot Fort, noted for its strategic defensive position and architectural significance.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e456274c888190ac80402e391674dd |
completed | April 19, 2026, 4:12 a.m. |
Created at: April 10, 2026, 5:50 a.m.