Triple
T19921586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DJI Avata |
E478807
|
entity |
| Predicate | maxFlightSpeed |
P2096
|
FINISHED |
| Object | approximately 27 m/s |
—
|
LITERAL 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: approximately 27 m/s | Statement: [DJI Avata, maxFlightSpeed, approximately 27 m/s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maxFlightSpeed Context triple: [DJI Avata, maxFlightSpeed, approximately 27 m/s]
-
A.
supercruiseSpeed
Indicates the speed at which an aircraft or vehicle can sustain supersonic flight without using afterburners or additional boost.
-
B.
maxSpeed
chosen
Indicates the greatest possible speed at which an entity can move or operate under specified conditions.
-
C.
maximumFlightDuration
Indicates the longest allowable or observed time period that a flight can continuously operate.
-
D.
stallSpeed
Indicates the minimum speed at which an aircraft (or similar vehicle) can fly while still maintaining sufficient lift to avoid stalling.
-
E.
maximumTakeoffWeight
Indicates the greatest allowable weight an aircraft can have at the start of its takeoff roll under specified conditions.
- F. None of above.
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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c6919c8190a96106532580b6b6 |
completed | April 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.