Triple
T10214285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Core Image |
E242402
|
entity |
| Predicate | primaryClass |
P81223
|
FINISHED |
| Object |
CIImage
CIImage is a Core Image class in Apple’s frameworks that represents image data for high-performance, GPU-accelerated image processing and filtering.
|
E849988
|
NE FINISHED |
How this triple was built (4 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: CIImage | Statement: [Core Image, primaryClass, CIImage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CIImage Context triple: [Core Image, primaryClass, CIImage]
-
A.
Core Image
Core Image is an Apple framework for high-performance image processing and analysis, offering GPU-accelerated filters and effects for macOS, iOS, and related platforms.
-
B.
WKInterfaceImage
WKInterfaceImage is a WatchKit user interface class used to display and manage images on Apple Watch app interfaces.
-
C.
imgCIF
imgCIF is a crystallographic data format designed to store and exchange image and diffraction data within the Crystallographic Information Framework.
-
D.
TImage
TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
-
E.
Quartz 2D
Quartz 2D is Apple’s modern 2D graphics rendering and drawing engine used in macOS and iOS for high-quality, resolution-independent graphics.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: CIImage Triple: [Core Image, primaryClass, CIImage]
Generated description
CIImage is a Core Image class in Apple’s frameworks that represents image data for high-performance, GPU-accelerated image processing and filtering.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CIImage Target entity description: CIImage is a Core Image class in Apple’s frameworks that represents image data for high-performance, GPU-accelerated image processing and filtering.
-
A.
Core Image
Core Image is an Apple framework for high-performance image processing and analysis, offering GPU-accelerated filters and effects for macOS, iOS, and related platforms.
-
B.
WKInterfaceImage
WKInterfaceImage is a WatchKit user interface class used to display and manage images on Apple Watch app interfaces.
-
C.
imgCIF
imgCIF is a crystallographic data format designed to store and exchange image and diffraction data within the Crystallographic Information Framework.
-
D.
TImage
TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
-
E.
Quartz 2D
Quartz 2D is Apple’s modern 2D graphics rendering and drawing engine used in macOS and iOS for high-quality, resolution-independent graphics.
- F. None of above. chosen
Provenance (5 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa273bdc8190bc4cf67a7923cebc |
completed | April 6, 2026, 12:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d652ea80dc81908bc65ee2ec390467 |
completed | April 8, 2026, 1:06 p.m. |
| NEDg | Description generation | batch_69d657818b008190a24170717cff53b9 |
completed | April 8, 2026, 1:26 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d65835a11c819083d069ab0f644d4c |
completed | April 8, 2026, 1:29 p.m. |
Created at: April 6, 2026, 11:04 a.m.