Charles Blundell
E911003
Charles Blundell is a machine learning researcher known for his contributions to deep learning and probabilistic modeling, including work on few-shot learning methods.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Charles Blundell canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003596 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Blundell Context triple: [Matching Networks for One Shot Learning, hasAuthor, Charles Blundell]
-
A.
Richard Bristow
Richard Bristow was a 16th-century English Catholic scholar and theologian who contributed to the development and annotation of the Douay–Rheims Bible.
-
B.
Paul Beeston
Paul Beeston is a prominent Canadian baseball executive best known for his long tenure as a top leader of the Toronto Blue Jays and as the first president of Major League Baseball.
-
C.
Charles Siddall
Charles Siddall was a family member of the Pre-Raphaelite-associated artist and poet Elizabeth Siddal, belonging to the same Victorian-era Siddall/Siddall family circle.
-
D.
David Brierley
David Brierley was a British actor best known for providing the voice of the robot dog K-9 in the classic science fiction television series Doctor Who.
-
E.
Christopher Greenbury
Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
- 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: Charles Blundell Target entity description: Charles Blundell is a machine learning researcher known for his contributions to deep learning and probabilistic modeling, including work on few-shot learning methods.
-
A.
Richard Bristow
Richard Bristow was a 16th-century English Catholic scholar and theologian who contributed to the development and annotation of the Douay–Rheims Bible.
-
B.
Paul Beeston
Paul Beeston is a prominent Canadian baseball executive best known for his long tenure as a top leader of the Toronto Blue Jays and as the first president of Major League Baseball.
-
C.
Charles Siddall
Charles Siddall was a family member of the Pre-Raphaelite-associated artist and poet Elizabeth Siddal, belonging to the same Victorian-era Siddall/Siddall family circle.
-
D.
David Brierley
David Brierley was a British actor best known for providing the voice of the robot dog K-9 in the classic science fiction television series Doctor Who.
-
E.
Christopher Greenbury
Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
machine learning researcher
ⓘ
person ⓘ |
| activeIn | 21st century ⓘ |
| affiliation | Google DeepMind NERFINISHED ⓘ |
| authorOf | Weight Uncertainty in Neural Networks NERFINISHED ⓘ |
| citizenship | United Kingdom ⓘ |
| coauthorWith |
Daan Wierstra
NERFINISHED
ⓘ
Danilo Rezende NERFINISHED ⓘ Demiang Kingma NERFINISHED ⓘ Koray Kavukcuoglu NERFINISHED ⓘ Oriol Vinyals NERFINISHED ⓘ Shakir Mohamed NERFINISHED ⓘ Yee Whye Teh NERFINISHED ⓘ |
| contributedTo | Bayes by Backprop NERFINISHED ⓘ |
| educatedAt |
University College London
ⓘ
Cambridge University ⓘ
surface form:
University of Cambridge
|
| employer | DeepMind NERFINISHED ⓘ |
| fieldOfStudy |
machine learning
ⓘ
statistics ⓘ |
| fieldOfWork |
Bayesian machine learning
ⓘ
deep learning ⓘ few-shot learning ⓘ machine learning ⓘ meta-learning ⓘ probabilistic modeling ⓘ |
| hasAcademicContribution |
applications of Bayesian methods to deep learning
ⓘ
development of Bayes by Backprop for neural networks ⓘ methods for few-shot and meta-learning in neural networks ⓘ |
| hasResearchInterest |
approximate Bayesian inference
ⓘ
few-shot generalization ⓘ probabilistic programming ⓘ representation learning ⓘ uncertainty in neural networks ⓘ |
| knownFor |
Bayesian neural networks
NERFINISHED
ⓘ
few-shot learning methods ⓘ probabilistic deep learning ⓘ variational inference methods for neural networks ⓘ |
| language | English ⓘ |
| memberOf | DeepMind research team NERFINISHED ⓘ |
| nationality | British ⓘ |
| notableWork | Weight Uncertainty in Neural Networks NERFINISHED ⓘ |
| publishedIn |
ICLR
NERFINISHED
ⓘ
ICML NERFINISHED ⓘ JMLR NERFINISHED ⓘ NeurIPS NERFINISHED ⓘ |
| role | research scientist ⓘ |
| worksAt | DeepMind NERFINISHED ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Charles Blundell Description of subject: Charles Blundell is a machine learning researcher known for his contributions to deep learning and probabilistic modeling, including work on few-shot learning methods.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.