Triple
T13179418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swift |
E313684
|
entity |
| Predicate | slewCapability |
P44396
|
FINISHED |
| Object | can slew to new targets in about 20–70 seconds |
—
|
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: can slew to new targets in about 20–70 seconds | Statement: [Swift, slewCapability, can slew to new targets in about 20–70 seconds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: slewCapability Context triple: [Swift, slewCapability, can slew to new targets in about 20–70 seconds]
-
A.
hasSlewRateTypical
chosen
Indicates that an entity is characterized by a specified typical (nominal) slew rate value.
-
B.
hasSlowMovement
Indicates that an entity exhibits movement that is slower than a normal or expected speed.
-
C.
apogeeCapability
Indicates the maximum altitude or apogee that an entity is capable of reaching or supporting.
-
D.
shutterSpeed
Indicates the exposure time setting of a camera, defining how long the shutter remains open during an image capture.
-
E.
gimbalCapability
Indicates the ability of a system or device to support and control a gimbal’s movement or stabilization functions.
- 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bc2c0c88190be357811aa8e828d |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:14 p.m.