Triple

T15555786
Position Surface form Disambiguated ID Type / Status
Subject Jian Sun E370862 entity
Predicate notablePublication P4 FINISHED
Object Deep Residual Learning for Image Recognition E74928 NE FINISHED

How this triple was built (2 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: Deep Residual Learning for Image Recognition | Statement: [Jian Sun, notablePublication, Deep Residual Learning for Image Recognition]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Deep Residual Learning for Image Recognition
Context triple: [Jian Sun, notablePublication, Deep Residual Learning for Image Recognition]
  • A. Very Deep Convolutional Networks for Large-Scale Image Recognition
    "Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
  • B. Aggregated Residual Transformations for Deep Neural Networks
    "Aggregated Residual Transformations for Deep Neural Networks" is the research paper that introduced the ResNeXt architecture, a deep convolutional neural network design that improves accuracy and efficiency by using grouped convolutions and aggregated residual transformations.
  • C. ResNet chosen
    ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
  • D. ImageNet Classification with Deep Convolutional Neural Networks
    "ImageNet Classification with Deep Convolutional Neural Networks" is the landmark 2012 research paper that introduced the deep CNN model AlexNet, demonstrating a dramatic leap in image recognition performance on the ImageNet benchmark and catalyzing the modern deep learning revolution in computer vision.
  • E. Inception architecture
    The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a97dbfc8190a98cbbac5e71ba88 completed April 16, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56bf8cac81909886de5b82849cb2 completed May 9, 2026, 3:46 p.m.
Created at: April 10, 2026, 4:09 a.m.