Triple

T10214150
Position Surface form Disambiguated ID Type / Status
Subject Metal Performance Shaders E242399 entity
Predicate supports P516 FINISHED
Object MPSCNNKernel
MPSCNNKernel is a core Metal Performance Shaders class that encapsulates and executes high-performance convolutional neural network operations on Apple GPUs.
 E849983 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: MPSCNNKernel | Statement: [Metal Performance Shaders, supports, MPSCNNKernel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MPSCNNKernel
Context triple: [Metal Performance Shaders, supports, MPSCNNKernel]
  • A. ShuffleNetV2
    ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
  • B. LeNet
    LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
  • C. NPU
    NPU is a leading Chinese research university in Xi’an renowned for its strengths in aeronautics, astronautics, and marine engineering.
  • D. NPU
    NPU is the commonly used abbreviation for the National Police of Ukraine, the country’s central law enforcement agency responsible for maintaining public order and safety.
  • E. MobileNetV2
    MobileNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, widely used in computer vision applications and available in libraries like torchvision.
  • 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: MPSCNNKernel
Triple: [Metal Performance Shaders, supports, MPSCNNKernel]
Generated description
MPSCNNKernel is a core Metal Performance Shaders class that encapsulates and executes high-performance convolutional neural network operations on Apple GPUs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MPSCNNKernel
Target entity description: MPSCNNKernel is a core Metal Performance Shaders class that encapsulates and executes high-performance convolutional neural network operations on Apple GPUs.
  • A. ShuffleNetV2
    ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
  • B. LeNet
    LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
  • C. NPU
    NPU is a leading Chinese research university in Xi’an renowned for its strengths in aeronautics, astronautics, and marine engineering.
  • D. NPU
    NPU is the commonly used abbreviation for the National Police of Ukraine, the country’s central law enforcement agency responsible for maintaining public order and safety.
  • E. MobileNetV2
    MobileNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, widely used in computer vision applications and available in libraries like torchvision.
  • 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_69d3aa24efc081909714d98943543283 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.