Triple
T20003961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CMSensorRecorder |
E494402
|
entity |
| Predicate | persistenceDuration |
P93788
|
FINISHED |
| Object | limited historical window (implementation-defined by iOS) |
—
|
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: limited historical window (implementation-defined by iOS) | Statement: [CMSensorRecorder, persistenceDuration, limited historical window (implementation-defined by iOS)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: persistenceDuration Context triple: [CMSensorRecorder, persistenceDuration, limited historical window (implementation-defined by iOS)]
-
A.
persistenceType
Indicates the manner or mode in which something continues to exist, endure, or remain over time.
-
B.
existencePeriod
Indicates the time span during which an entity exists or is valid.
-
C.
persistence
Indicates a continued or repeated existence, occurrence, or effort of something over time despite potential changes or obstacles.
-
D.
persistsAfter
Indicates that one state, condition, or effect continues to exist after a specified event, time point, or other state has occurred or ended.
-
E.
dataRetentionPeriod
chosen
Indicates the length of time data is stored or kept before it is deleted, archived, or otherwise disposed of.
- 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_69e661a3ad148190918f9dce755fe470 |
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.