Triple
T20003174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Do Not Disturb While Driving in iOS 11 |
E494385
|
entity |
| Predicate | autoReplyAudience |
P485
|
FINISHED |
| Object | favorites |
—
|
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: favorites | Statement: [Do Not Disturb While Driving in iOS 11, autoReplyAudience, favorites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: autoReplyAudience Context triple: [Do Not Disturb While Driving in iOS 11, autoReplyAudience, favorites]
-
A.
scopeOfRecipients
chosen
Indicates the range or group of recipients to whom something (such as information, communication, or benefits) is directed or applicable.
-
B.
intendedAudienceInteraction
Indicates that one entity is the target group or audience with whom another entity is meant to interact or engage.
-
C.
knownOnlyToAudienceAs
Indicates that certain information about an entity is available to and recognized by the audience but not known or accessible to other entities within the context.
-
D.
recipientsMayUse
Indicates that recipients are permitted to use something (e.g., content, data, or resources) under specified conditions.
-
E.
addresseeOf
Indicates that one entity is the intended recipient or target audience of a communication, message, or expression from 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a2e34481908a495cc5d077c41f |
completed | April 20, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:33 p.m.