Triple
T11160556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snap Map |
E264023
|
entity |
| Predicate | privacyControl |
P15689
|
FINISHED |
| Object | Ghost Mode |
—
|
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: Ghost Mode | Statement: [Snap Map, privacyControl, Ghost Mode]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: privacyControl Context triple: [Snap Map, privacyControl, Ghost Mode]
-
A.
privacyProperty
Indicates that one entity has a characteristic, rule, or condition specifically related to privacy in the context of the relationship.
-
B.
privacyCharacteristic
chosen
Indicates the specific privacy-related property or feature that characterizes how information is handled, protected, or exposed in a given context.
-
C.
dataPolicy
Indicates that one entity defines or governs how data related to another entity is collected, used, stored, or shared.
-
D.
privacyPolicyURL
Indicates the web address where the privacy policy governing data collection and use can be accessed.
-
E.
dataSegregation
Indicates that data is kept separate or partitioned so that information from one group, context, or user is not mixed or accessible with that of 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8817a90819087820d5241c58851 |
completed | April 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69d75cec26fc8190a5497d186306f935 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.