Triple

T18016487
Position Surface form Disambiguated ID Type / Status
Subject Faster R-CNN E431008 entity
Predicate influenced P9 FINISHED
Object Feature Pyramid Networks based detectors — NE NERFINISHED

Named-entity recognition

Before disambiguation, gpt-5-mini classified whether the object phrase is a named entity — the step behind the object's NE type shown above.

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: Feature Pyramid Networks based detectors | Statement: [Faster R-CNN, influenced, Feature Pyramid Networks based detectors]

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: Feature Pyramid Networks based detectors
Context triple: [Faster R-CNN, influenced, Feature Pyramid Networks based detectors]
  • A. FasterRCNN
    FasterRCNN is a popular two-stage object detection architecture that first proposes candidate regions and then classifies and refines bounding boxes, widely used in computer vision tasks.
  • B. R-CNN
    R-CNN is a pioneering deep learning framework for object detection that combines region proposals with convolutional neural networks to accurately localize and classify objects in images.
  • C. RCNN
    RCNN is the ICAO airport code assigned to Tainan Airport in Tainan, Taiwan.
  • D. RetinaNet
    RetinaNet is a deep learning–based one-stage object detection model known for its focal loss function, which effectively addresses class imbalance to achieve high accuracy and speed.
  • E. MaskRCNN
    MaskRCNN is a deep learning model architecture for instance segmentation that extends Faster R-CNN by adding a branch to predict segmentation masks for individual objects in an image.
  • 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: Feature Pyramid Networks based detectors
Target entity description: Feature Pyramid Networks based detectors are a family of object detection models that enhance multi-scale feature representation by building top-down feature hierarchies with lateral connections, improving accuracy for objects of varying sizes.
  • A. FasterRCNN
    FasterRCNN is a popular two-stage object detection architecture that first proposes candidate regions and then classifies and refines bounding boxes, widely used in computer vision tasks.
  • B. R-CNN
    R-CNN is a pioneering deep learning framework for object detection that combines region proposals with convolutional neural networks to accurately localize and classify objects in images.
  • C. RCNN
    RCNN is the ICAO airport code assigned to Tainan Airport in Tainan, Taiwan.
  • D. RetinaNet
    RetinaNet is a deep learning–based one-stage object detection model known for its focal loss function, which effectively addresses class imbalance to achieve high accuracy and speed.
  • E. MaskRCNN
    MaskRCNN is a deep learning model architecture for instance segmentation that extends Faster R-CNN by adding a branch to predict segmentation masks for individual objects in an image.
  • F. None of above. chosen

Provenance (2 batches)

Stage Batch ID Job type Status
creating batch_69d8b904530081908bf341d842464856 elicitation completed
NER batch_69e4b9be5d0c819097e006f32d98753a ner completed
Created at: April 10, 2026, 10:24 a.m.