Triple

T15361373
Position Surface form Disambiguated ID Type / Status
Subject Xiangyu Zhang E367296 entity
Predicate knownFor P22 FINISHED
Object ShuffleNet architecture
ShuffleNet architecture is a family of highly efficient convolutional neural networks designed for mobile and embedded devices, using channel shuffle and grouped convolutions to achieve strong accuracy with very low computational cost.
 E431006 NE FINISHED

Disambiguation candidates (2 decisions)

The exact options the model was shown at each disambiguation step, with the option it chose highlighted — the evidence behind this triple's disambiguated ids.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ShuffleNet architecture
Context triple: [Xiangyu Zhang, knownFor, ShuffleNet architecture]
  • 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. SqueezeNet
    SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
  • C. 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.
  • D. NASNet
    NASNet is a family of convolutional neural network architectures automatically discovered via neural architecture search, known for achieving state-of-the-art performance on image classification benchmarks.
  • E. Learning Transferable Architectures for Scalable Image Recognition
    "Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ShuffleNet architecture
Target entity description: ShuffleNet architecture is a family of highly efficient convolutional neural networks designed for mobile and embedded devices, using channel shuffle and grouped convolutions to achieve strong accuracy with very low computational cost.
  • A. ShuffleNetV2 chosen
    ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
  • B. SqueezeNet
    SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
  • C. 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.
  • D. NASNet
    NASNet is a family of convolutional neural network architectures automatically discovered via neural architecture search, known for achieving state-of-the-art performance on image classification benchmarks.
  • E. Learning Transferable Architectures for Scalable Image Recognition
    "Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
  • F. None of above.

Provenance (5 batches)

Stage Batch ID Job type Status
creating batch_69d85a1483788190ad93c2748e8af34b elicitation completed
NER batch_69e03e4607408190ab281a7f7a8012d3 ner completed
NED1 batch_69ff0b4a181c8190bffc1ac1a86e215d ned_source_triple completed
NED2 batch_69ff0fd586708190a54b33efd27d84b2 ned_description completed
NEDg batch_69ff0f82441c81909a8ae13817fd3e96 nedg completed
Created at: April 10, 2026, 3:18 a.m.