Triple
T19965384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DJI Agras |
E479916
|
entity |
| Predicate | hasModel |
P2390
|
FINISHED |
| Object | DJI Agras T10 |
—
|
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: DJI Agras T10 | Statement: [DJI Agras, hasModel, DJI Agras T10]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DJI Agras T10 Context triple: [DJI Agras, hasModel, DJI Agras T10]
-
A.
DJI Agras
chosen
DJI Agras is a series of agricultural drones designed for tasks like crop spraying, seeding, and precision farming.
-
B.
DJI Avata
DJI Avata is a compact first-person-view (FPV) camera drone designed for immersive, agile flight and stabilized aerial video.
-
C.
DJI Inspire
DJI Inspire is a professional-grade series of camera drones known for advanced aerial cinematography capabilities and high-performance flight features.
-
D.
DJI
DJI is a leading Chinese technology company best known worldwide for manufacturing consumer and professional drones and aerial imaging systems.
-
E.
DJI RSC 3
The DJI RSC 3 is a compact, foldable 3-axis camera gimbal stabilizer designed for mirrorless and DSLR cameras, offering advanced stabilization and intelligent shooting modes for professional-quality video.
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65bc4f47c8190a721f5e488150d81 |
completed | April 20, 2026, 5 p.m. |
Created at: April 10, 2026, 1:54 p.m.