Triple
T11351798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple M2 iPad Air (5th generation) |
E268854
|
entity |
| Predicate | supportsCellularVariant |
P46630
|
FINISHED |
| Object | 5G |
—
|
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: 5G | Statement: [Apple M2 iPad Air (5th generation), supportsCellularVariant, 5G]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsCellularVariant Context triple: [Apple M2 iPad Air (5th generation), supportsCellularVariant, 5G]
-
A.
hasCellularComponent
Indicates that an entity possesses, includes, or is associated with a specific cellular component as part of its structure or organization.
-
B.
supportsEsim
Indicates that one entity provides compatibility with, or the ability to use, an embedded SIM (eSIM) for another entity.
-
C.
hasCellService
chosen
Indicates that a location, device, or area is within range of a cellular network and can access mobile phone or data services.
-
D.
supportsNetworkingModel
Indicates that one entity provides compatibility with, or implementation of, a specified networking model for another entity.
-
E.
supportsModelVariant
Indicates that one entity is capable of operating with, being compatible with, or otherwise accommodating a specific variant of a model.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.