Aristo
E366088
Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Aristo canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T3520109 — 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: Aristo Context triple: [Allen Institute for Artificial Intelligence, hasResearchProgram, Aristo]
-
A.
Apollo Actius
Apollo Actius is a local epithet of the Greek god Apollo venerated at Actium, especially associated with the sanctuary overlooking the site of the famous naval battle between Octavian and Antony.
-
B.
Aristocles
Aristocles was the given birth name of the ancient Greek philosopher Plato, one of the most influential figures in Western philosophy.
-
C.
Cotta
Cotta is a German publishing house historically known for issuing influential literary and philosophical works, including those of major figures like Goethe and Schiller.
-
D.
Antipater of Sidon
Antipater of Sidon was a 2nd-century BCE Greek poet best known for his epigrams and for composing one of the earliest surviving lists praising the Seven Wonders of the Ancient World.
-
E.
Hipparchicus
Hipparchicus is an ancient Greek treatise by Xenophon that provides practical guidance on the duties and conduct of a cavalry commander.
- 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: Aristo Target entity description: Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
-
A.
Apollo Actius
Apollo Actius is a local epithet of the Greek god Apollo venerated at Actium, especially associated with the sanctuary overlooking the site of the famous naval battle between Octavian and Antony.
-
B.
Aristocles
Aristocles was the given birth name of the ancient Greek philosopher Plato, one of the most influential figures in Western philosophy.
-
C.
Cotta
Cotta is a German publishing house historically known for issuing influential literary and philosophical works, including those of major figures like Goethe and Schiller.
-
D.
Antipater of Sidon
Antipater of Sidon was a 2nd-century BCE Greek poet best known for his epigrams and for composing one of the earliest surviving lists praising the Seven Wonders of the Ancient World.
-
E.
Hipparchicus
Hipparchicus is an ancient Greek treatise by Xenophon that provides practical guidance on the duties and conduct of a cavalry commander.
- F. None of above. chosen
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
AI research project
ⓘ
question answering system ⓘ |
| affiliation |
Paul G. Allen School of Computer Science & Engineering
ⓘ
surface form:
Paul G. Allen School of Computer Science & Engineering (collaborations)
|
| aimsTo |
advance AI for science education tools
ⓘ
model scientific knowledge ⓘ perform explanation-oriented reasoning ⓘ |
| approach |
combination of NLP and reasoning modules
ⓘ
ensemble of specialized solvers ⓘ |
| basedIn |
Seattle
ⓘ
Washington ⓘ |
| country |
United States of America
ⓘ
surface form:
United States
|
| developer |
AI2
ⓘ
Allen Institute for Artificial Intelligence ⓘ |
| domain |
K-12 science
ⓘ
science education ⓘ |
| evaluation |
public science QA benchmarks
ⓘ
standardized school science exams ⓘ |
| field |
artificial intelligence
ⓘ
automated reasoning ⓘ natural language processing ⓘ question answering ⓘ |
| fundingType | research project ⓘ |
| goal |
achieve high performance on standardized tests
ⓘ
answer multiple-choice science questions ⓘ demonstrate machine reasoning over science text ⓘ |
| language | English ⓘ |
| notableFor |
performance on 12th grade science exams
ⓘ
performance on 8th grade science exams ⓘ standardized science test benchmarks ⓘ |
| organization | Allen Institute for Artificial Intelligence ⓘ |
| publicationType | peer-reviewed research papers ⓘ |
| researchFocus |
commonsense reasoning for science
ⓘ
multi-step reasoning ⓘ natural language understanding ⓘ science question answering ⓘ solving standardized math exams ⓘ solving standardized science exams ⓘ |
| task |
diagram and table understanding (science contexts)
ⓘ
multiple-choice question answering ⓘ reading comprehension for science ⓘ |
| uses |
information retrieval
ⓘ
knowledge bases ⓘ machine learning ⓘ natural language understanding ⓘ symbolic reasoning ⓘ |
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: Aristo Description of subject: Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.