Triple
T38697973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nokia Belle Feature Pack 1 |
E950056
|
entity |
| Predicate | targetDevicesBrand |
P42355
|
FINISHED |
| Object | Nokia |
—
|
NE NERFINISHED |
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: Nokia | Statement: [Nokia Belle Feature Pack 1, targetDevicesBrand, Nokia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetDevicesBrand Context triple: [Nokia Belle Feature Pack 1, targetDevicesBrand, Nokia]
-
A.
marketsDevicesUnderBrand
chosen
Indicates that an entity promotes and sells devices using a particular brand name or under a specific brand identity.
-
B.
includesDevices
Indicates that one entity contains, encompasses, or has as part of it one or more devices.
-
C.
targetVendorDevice
Indicates that a device is specifically associated with or designated as the target device for a particular vendor.
-
D.
targetedDevice
Indicates that one entity is the specific device toward which another entity’s action, effect, or configuration is directed.
-
E.
targetedDeviceType
Indicates the specific type or category of device that is the intended target of an action, configuration, or content.
- 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_69f76f0124408190bb39c3040734846b |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ff6ef0d61c81909162d37c15a1a3c3 |
completed | May 9, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69ff6c6a58e08190921317062cd9d489 |
completed | May 9, 2026, 5:18 p.m. |
Created at: May 3, 2026, 4:33 p.m.