Triple

T18016324
Position Surface form Disambiguated ID Type / Status
Subject MobileNetV2 E431005 entity
Predicate availableInLibrary P57368 FINISHED
Object Keras Applications NE NERFINISHED

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: Keras Applications | Statement: [MobileNetV2, availableInLibrary, Keras Applications]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keras Applications
Context triple: [MobileNetV2, availableInLibrary, Keras Applications]
  • A. Keras chosen
    Keras is a high-level neural networks API written in Python that simplifies building, training, and deploying deep learning models, often running on top of frameworks like TensorFlow.
  • B. TensorFlow Hub
    TensorFlow Hub is a library and online repository of reusable machine learning models and components designed to simplify sharing and deploying pretrained models in TensorFlow applications.
  • C. TensorFlow Model Garden
    TensorFlow Model Garden is a curated collection of state-of-the-art machine learning models, reference implementations, and examples built using TensorFlow to help developers train, evaluate, and deploy advanced AI solutions.
  • D. Caffe Model Zoo
    Caffe Model Zoo is a public collection of pre-trained deep learning models shared by the Caffe community for tasks like image classification, detection, and segmentation.
  • E. GoogLeNet
    GoogLeNet is a deep convolutional neural network developed by Google that popularized the Inception architecture and achieved state-of-the-art performance in image recognition tasks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b523f588819097389e067dda7f23 completed April 19, 2026, 10:57 a.m.
Created at: April 10, 2026, 10:24 a.m.