Triple
T18016561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RetinaNet |
E431010
|
entity |
| Predicate | usesComponent |
P35
|
FINISHED |
| Object | Feature Pyramid Network |
—
|
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: Feature Pyramid Network | Statement: [RetinaNet, usesComponent, Feature Pyramid Network]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Feature Pyramid Network Context triple: [RetinaNet, usesComponent, Feature Pyramid Network]
-
A.
Feature Pyramid Networks based detectors
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.
-
B.
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.
-
C.
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.
-
D.
RCNN
RCNN is the ICAO airport code assigned to Tainan Airport in Tainan, Taiwan.
-
E.
FPN
chosen
FPN (Feature Pyramid Network) is a neural network architecture component that builds multi-scale feature maps to improve object detection performance, especially for detecting objects at different sizes.
- 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_69e4b9be5d0c819097e006f32d98753a |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 10:24 a.m.