Triple
T1368007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adobe Photoshop |
E30045
|
entity |
| Predicate | hasAIFeature |
P17640
|
FINISHED |
| Object |
Neural Filters
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
|
E155907
|
NE FINISHED |
How this triple was built (5 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: Neural Filters | Statement: [Adobe Photoshop, hasAIFeature, Neural Filters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neural Filters Context triple: [Adobe Photoshop, hasAIFeature, Neural Filters]
-
A.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
B.
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.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Neural Filters Triple: [Adobe Photoshop, hasAIFeature, Neural Filters]
Generated description
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Neural Filters Target entity description: Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
-
A.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
B.
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.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAIFeature Context triple: [Adobe Photoshop, hasAIFeature, Neural Filters]
-
A.
hasFeature
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
B.
hasAIPhotoFeatures
chosen
Indicates that an entity provides or supports photo-related features powered by artificial intelligence.
-
C.
supportsFeature
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
D.
technologicalFeature
Indicates that one entity possesses, exhibits, or is characterized by a specific technological capability, component, or functionality in relation to another entity.
-
E.
featuresSupporter
Indicates that one entity serves as a supporter, advocate, or promoter of another entity or its cause.
- F. None of above.
Provenance (6 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_69a498f912008190a376a98b207b2071 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c2d497f88190993d16a208ced43d |
completed | March 1, 2026, 10:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acce788098819087a046e10966b7e9 |
completed | March 8, 2026, 1:18 a.m. |
| NEDg | Description generation | batch_69accf15d910819098e9a4b24247881b |
completed | March 8, 2026, 1:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69accffa9a40819083a3e55a5d83e040 |
completed | March 8, 2026, 1:25 a.m. |
| PD | Predicate disambiguation | batch_69a4befb08b88190be966fa1aadd4bcd |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:57 p.m.