Triple
T36796579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snap Ads |
E909199
|
entity |
| Predicate | primaryDeviceType |
P193309
|
FINISHED |
| Object | mobile |
—
|
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: mobile | Statement: [Snap Ads, primaryDeviceType, mobile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDeviceType Context triple: [Snap Ads, primaryDeviceType, mobile]
-
A.
primaryDeviceCategory
Indicates the main type or class of device associated with an entity or event, distinguishing it from other possible device categories.
-
B.
targetedDeviceType
chosen
Indicates the specific type or category of device that is the intended target of an action, configuration, or content.
-
C.
primarySystem
Indicates that one system is designated as the main or most important system in relation to another system or context.
-
D.
testedDeviceType
Indicates that one entity is the type or category of device on which another entity has been tested.
-
E.
targetedDevice
Indicates that one entity is the specific device toward which another entity’s action, effect, or configuration is directed.
- 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_69f76e7b98888190899b6478a82ad6ae |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:12 p.m.