Triple
T3426859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Home ecosystem |
E72246
|
entity |
| Predicate | supportsUserRecognition |
P15551
|
FINISHED |
| Object | voice match |
—
|
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 match | Statement: [Google Home ecosystem, supportsUserRecognition, voice match]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsUserRecognition Context triple: [Google Home ecosystem, supportsUserRecognition, voice match]
-
A.
canRecognize
chosen
Indicates that one entity has the ability to identify or distinguish another entity based on its features or characteristics.
-
B.
hasProcessOfRecognition
Indicates that one entity is involved in or characterized by a process of recognizing, identifying, or acknowledging another entity or condition.
-
C.
hasFaceUnlock
Indicates that an entity supports or is equipped with a facial recognition–based unlocking feature.
-
D.
areRecognizedBy
Indicates that one entity acknowledges, identifies, or accepts another entity as valid, known, or legitimate.
-
E.
recognizedFor
Indicates that one entity is acknowledged, credited, or honored for a particular achievement, quality, contribution, or work associated with another entity.
- 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.