Triple
T9027828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | App Clips |
E216090
|
entity |
| Predicate | permissionModel |
P11330
|
FINISHED |
| Object | same system permissions model as full apps |
—
|
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: same system permissions model as full apps | Statement: [App Clips, permissionModel, same system permissions model as full apps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: permissionModel Context triple: [App Clips, permissionModel, same system permissions model as full apps]
-
A.
permitType
Indicates the specific category or kind of permit associated with an entity or activity.
-
B.
hasAccessModel
Indicates that one entity is permitted to use, interact with, or retrieve a particular model controlled by another entity or system.
-
C.
usesPolicyModel
chosen
Indicates that one entity applies, relies on, or operates according to a particular policy model.
-
D.
authorityGranted
Indicates that one entity has formally given another entity the power, rights, or permission to act or make decisions, typically within a defined scope or context.
-
E.
securityRole
Indicates that an entity holds a specific security-related role, permission level, or access profile within a system or context.
- 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_69ca83a5fa88819088144801b4dd7245 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a7fcb308190af90d6be8700e498 |
completed | April 1, 2026, 12:44 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee132f08190940749c7c522e4c1 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:07 p.m.