Triple
T10522763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KJ-500 |
E248216
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Shaanxi Y-9 |
E621383
|
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: Shaanxi Y-9 | Statement: [KJ-500, basedOn, Shaanxi Y-9]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shaanxi Y-9 Context triple: [KJ-500, basedOn, Shaanxi Y-9]
-
A.
Shaanxi Y-8
chosen
The Shaanxi Y-8 is a Chinese medium-sized, four-engine turboprop military transport aircraft widely used for cargo, troop transport, and specialized mission variants.
-
B.
Xian H-6
The Xian H-6 is a Chinese license-built version of the Soviet Tu-16 strategic bomber, extensively modernized and used for long-range strike and maritime attack roles.
-
C.
Hongdu JL-8
The Hongdu JL-8 is a Chinese-designed jet trainer and light attack aircraft developed to provide an affordable, modern training platform for fighter pilots.
-
D.
Nanchang A-5
The Nanchang A-5 is a Chinese-built, twin-engine ground-attack and light bomber aircraft developed from the Shenyang J-6 fighter and exported to several countries for close air support roles.
-
E.
Ye-6S
Ye-6S was a Soviet spacecraft bus platform used for early lunar orbiters such as Luna 10 during the space race.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509e0907481908807dd99980cba1f |
completed | April 7, 2026, 1:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90e1c73208190aa3d3e30aa4482ac |
completed | April 10, 2026, 2:50 p.m. |
Created at: April 6, 2026, 12:29 p.m.