Triple
T956994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tesla Powerwall |
E20645
|
entity |
| Predicate | communicationInterface |
P2798
|
FINISHED |
| Object | Wi-Fi |
—
|
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: Wi-Fi | Statement: [Tesla Powerwall, communicationInterface, Wi-Fi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: communicationInterface Context triple: [Tesla Powerwall, communicationInterface, Wi-Fi]
-
A.
communicationChannel
chosen
Indicates a medium or method through which information is transmitted between parties.
-
B.
communicationMode
Indicates the method or channel through which communication between entities is carried out.
-
C.
communicationStatus
Indicates the current state or condition of a communication process or exchange between entities (e.g., pending, active, failed, completed).
-
D.
communicationModelRole
Indicates the role an entity plays within a communication model, specifying its function or position in the communication process.
-
E.
telecommunicationSystem
Indicates a relationship where communication between entities is carried out over a distance using electronic or digital transmission systems.
- 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_69a493b21f2881908132dcf45dcd2f36 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3f981bc819098125554eeeb6375 |
completed | March 1, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a18ecc8190883f6206fe3b0fb6 |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.