Triple

T8820745
Position Surface form Disambiguated ID Type / Status
Subject SceneKit E209895 entity
Predicate hasClass P9272 FINISHED
Object SCNScene
SCNScene is a core SceneKit class that represents and manages a 3D scene graph, including its nodes, geometry, lights, and cameras.
 E759674 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: SCNScene | Statement: [SceneKit, hasClass, SCNScene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SCNScene
Context triple: [SceneKit, hasClass, SCNScene]
  • A. SceneKit
    SceneKit is a high-level 3D graphics framework from Apple used to build and render interactive 3D scenes and animations across its platforms.
  • B. SpriteKit
    SpriteKit is Apple’s 2D game development framework designed for building high-performance, animated games and interactive content across its platforms.
  • C. SKCameraNode
    SKCameraNode is a SpriteKit node class that represents a virtual camera used to control what portion of a 2D scene is visible on screen.
  • D. RealityKit
    RealityKit is Apple’s high-level 3D rendering and augmented reality framework used to build immersive spatial experiences on platforms like visionOS.
  • E. SKNode
    SKNode is the fundamental building-block class in Apple's SpriteKit framework, representing a node in a scene graph that can display content or act as a container for other nodes.
  • 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: SCNScene
Triple: [SceneKit, hasClass, SCNScene]
Generated description
SCNScene is a core SceneKit class that represents and manages a 3D scene graph, including its nodes, geometry, lights, and cameras.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SCNScene
Target entity description: SCNScene is a core SceneKit class that represents and manages a 3D scene graph, including its nodes, geometry, lights, and cameras.
  • A. SceneKit
    SceneKit is a high-level 3D graphics framework from Apple used to build and render interactive 3D scenes and animations across its platforms.
  • B. SpriteKit
    SpriteKit is Apple’s 2D game development framework designed for building high-performance, animated games and interactive content across its platforms.
  • C. SKCameraNode
    SKCameraNode is a SpriteKit node class that represents a virtual camera used to control what portion of a 2D scene is visible on screen.
  • D. RealityKit
    RealityKit is Apple’s high-level 3D rendering and augmented reality framework used to build immersive spatial experiences on platforms like visionOS.
  • E. SKNode
    SKNode is the fundamental building-block class in Apple's SpriteKit framework, representing a node in a scene graph that can display content or act as a container for other nodes.
  • 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_69ca8364e13081909c85fe80f44fe86f completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc601126248190b6f10c22f1aeac9a completed April 1, 2026, midnight
NED1 Entity disambiguation (via context triple) batch_69cf6fd064208190b1c8e1e1848763d2 completed April 3, 2026, 7:44 a.m.
NEDg Description generation batch_69cf71e0bd14819089a9667d573f2295 completed April 3, 2026, 7:53 a.m.
NED2 Entity disambiguation (via description) batch_69cf743758c881909eecaf9bdbb047e5 completed April 3, 2026, 8:03 a.m.
Created at: March 30, 2026, 6:46 p.m.