Triple
T2152570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Face ID |
E47811
|
entity |
| Predicate | privacyPolicy |
P10529
|
FINISHED |
| Object | facial recognition processing done on-device |
—
|
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: facial recognition processing done on-device | Statement: [Face ID, privacyPolicy, facial recognition processing done on-device]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: privacyPolicy Context triple: [Face ID, privacyPolicy, facial recognition processing done on-device]
-
A.
privacyProperty
Indicates that one entity has a characteristic, rule, or condition specifically related to privacy in the context of the relationship.
-
B.
dataPolicy
chosen
Indicates that one entity defines or governs how data related to another entity is collected, used, stored, or shared.
-
C.
privacyCharacteristic
Indicates the specific privacy-related property or feature that characterizes how information is handled, protected, or exposed in a given context.
-
D.
explainsPolicy
Indicates that one entity provides a clarification or detailed description of a policy to another entity.
-
E.
contactPolicy
Indicates the rules or constraints governing how and when one party is allowed to initiate or maintain contact with another.
- 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe48ad148190a7d6cc88fd38a660 |
completed | March 7, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69abbd9a60648190b20b116be5c7ad98 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.