Triple
T3426897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Works with Google Assistant |
E72247
|
entity |
| Predicate | supportsControlVia |
P11061
|
FINISHED |
| Object | voice commands |
—
|
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: voice commands | Statement: [Works with Google Assistant, supportsControlVia, voice commands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsControlVia Context triple: [Works with Google Assistant, supportsControlVia, voice commands]
-
A.
canControl
Indicates that one entity has the ability or authority to direct, manage, or influence the behavior or state of another entity.
-
B.
exportControl
Indicates that an entity is subject to rules or restrictions governing the transfer or export of goods, services, or information across borders.
-
C.
controlFrom
Indicates that one entity exercises authority, influence, or regulatory power over another entity or process.
-
D.
supportsCommand
chosen
Indicates that one entity is capable of recognizing, accepting, or executing a specified command associated with another entity.
-
E.
hasMotionControls
Indicates that an entity supports or involves control through physical movement or gestures rather than (or in addition to) traditional input methods.
- 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_69ad85ae14308190bcbc25cfa0246c0b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb982792c8190b1163eee4252210f |
completed | March 8, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69adadfea024819094b41a13bc004bda |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:15 p.m.