Triple
T30300340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Mode in iOS 13 |
E770635
|
entity |
| Predicate | exposesAPITo |
P167383
|
FINISHED |
| Object | third-party developers |
—
|
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: third-party developers | Statement: [Dark Mode in iOS 13, exposesAPITo, third-party developers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exposesAPITo Context triple: [Dark Mode in iOS 13, exposesAPITo, third-party developers]
-
A.
exposesTo
Indicates that one entity subjects another entity to contact with or influence from something, typically involving risk, effect, or experience.
-
B.
exposesFunction
chosen
Indicates that one entity makes a function available for use or access by another entity or context.
-
C.
exposedAs
Indicates that one entity reveals or publicly identifies another entity as having a hidden, false, or previously concealed role, identity, or nature.
-
D.
exposedThrough
Indicates that something becomes revealed, accessible, or affected as a result of passing through or being subjected to another thing or medium.
-
E.
exposes
Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
- 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_69f224881b948190b8c4921b250a44a3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6813a47dc81908cc75bae4d2b97cc |
completed | May 2, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69f678ce54b081908c26edfd49e39c60 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 7:48 p.m.