Triple
T3479044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Play Protect |
E73445
|
entity |
| Predicate | canDisable |
P23641
|
FINISHED |
| Object | specific apps identified as harmful |
—
|
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: specific apps identified as harmful | Statement: [Google Play Protect, canDisable, specific apps identified as harmful]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canDisable Context triple: [Google Play Protect, canDisable, specific apps identified as harmful]
-
A.
canBeDisabledOn
chosen
Indicates that a feature, function, or capability has the property that it can be turned off or deactivated when applied to the referenced entity.
-
B.
canUse
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
-
C.
canElect
Indicates that one entity has the authority or ability to choose another entity for a position, role, or office through an election process.
-
D.
canBlock
Indicates that one entity has the ability or permission to prevent, obstruct, or stop the action or effect of another entity.
-
E.
canMake
Indicates that one entity has the ability or capacity to create, produce, or assemble another entity.
- 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_69ad85b3c9b08190857cae74c7f36da9 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb5ca73c81908256e3339a3a6f9f |
completed | March 8, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69adae0935ac8190bfa8a8bd3dcd3301 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:17 p.m.