Triple
T21060794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SKTexture |
E518841
|
entity |
| Predicate | canBeCreatedFrom |
P23101
|
FINISHED |
| Object |
CGImage
CGImage is a Core Graphics data type in Apple’s frameworks that represents bitmap-based image data at a low level for rendering and image processing.
|
E1465230
|
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: CGImage | Statement: [SKTexture, canBeCreatedFrom, CGImage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CGImage Context triple: [SKTexture, canBeCreatedFrom, CGImage]
-
A.
CIImage
CIImage is a Core Image class in Apple’s frameworks that represents image data for high-performance, GPU-accelerated image processing and filtering.
-
B.
NSImage
NSImage is a Cocoa framework class in macOS used to represent and manage image data for display in graphical user interfaces.
-
C.
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.
-
D.
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.
-
E.
TImage
TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
- 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: CGImage Triple: [SKTexture, canBeCreatedFrom, CGImage]
Generated description
CGImage is a Core Graphics data type in Apple’s frameworks that represents bitmap-based image data at a low level for rendering and image processing.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CGImage Target entity description: CGImage is a Core Graphics data type in Apple’s frameworks that represents bitmap-based image data at a low level for rendering and image processing.
-
A.
CIImage
CIImage is a Core Image class in Apple’s frameworks that represents image data for high-performance, GPU-accelerated image processing and filtering.
-
B.
NSImage
NSImage is a Cocoa framework class in macOS used to represent and manage image data for display in graphical user interfaces.
-
C.
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.
-
D.
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.
-
E.
TImage
TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
- 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_69e0b505ef108190b25dd4033e2ff7eb |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6feaf3edc81909423e039cac6bd87 |
completed | April 21, 2026, 4:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09506d7de881909dd7564628f142e5 |
completed | May 17, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_6a09532354a48190bc275453ec866126 |
completed | May 17, 2026, 5:33 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a095382a3808190ae6efd040225fbdd |
completed | May 17, 2026, 5:34 a.m. |
Created at: April 16, 2026, 2:37 p.m.