Triple
T16707364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virgin Media O2 |
E406005
|
entity |
| Predicate | mobileNetworkGeneration |
P9898
|
FINISHED |
| Object | 4G |
—
|
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: 4G | Statement: [Virgin Media O2, mobileNetworkGeneration, 4G]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mobileNetworkGeneration Context triple: [Virgin Media O2, mobileNetworkGeneration, 4G]
-
A.
targetDeviceGeneration
Indicates the specific hardware or model generation of the device that is the focus or recipient of an action or relationship.
-
B.
technologyGeneration
chosen
Indicates the generational level or era of technology associated with or used by an entity in relation to another.
-
C.
cellularOptions
Indicates that one entity specifies or provides available cellular network or mobile connectivity options for another entity.
-
D.
hasCellularModel
Indicates that one entity serves as a cellular (cell-based) model or system used to study, represent, or simulate the biological properties or behavior of another entity.
-
E.
thirdGenerationPlatform
Indicates that the subject is a third-generation instance or version within a sequence of related platforms.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38337ecac8190bc4a9410ed7681ab |
completed | April 18, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.