Aristo project
E366085
AI research project
Allen Institute for Artificial Intelligence project
natural language processing system
question-answering system
The Aristo project is an AI research initiative by the Allen Institute for Artificial Intelligence focused on building systems that can answer and reason about standardized science exam questions.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Aristo project canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3520097 — 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 project Context triple: [Allen Institute for Artificial Intelligence, knownFor, Aristo project]
-
A.
Helios program
The Helios program was a joint NASA–German Aerospace Center mission in the 1970s that launched two probes to study the Sun at close range, setting records for both solar proximity and spacecraft speed.
-
B.
Proteus
Proteus is the nickname of Charles Proteus Steinmetz, a pioneering German-American electrical engineer and mathematician renowned for his foundational work in alternating current (AC) power systems.
-
C.
Proteus
Proteus is an experimental high-altitude, long-endurance aircraft designed by Scaled Composites for telecommunications, reconnaissance, and research missions.
-
D.
Proteus
Proteus is one of Neptune’s largest irregularly shaped moons, known for its dark surface and heavily cratered, ancient terrain.
-
E.
Aien Aristeuein
Aien Aristeuein is the ancient Greek motto of the University of St Andrews, traditionally translated as "Ever to Excel" and expressing a commitment to continual striving for excellence.
- 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 project Target entity description: The Aristo project is an AI research initiative by the Allen Institute for Artificial Intelligence focused on building systems that can answer and reason about standardized science exam questions.
-
A.
Helios program
The Helios program was a joint NASA–German Aerospace Center mission in the 1970s that launched two probes to study the Sun at close range, setting records for both solar proximity and spacecraft speed.
-
B.
Proteus
Proteus is the nickname of Charles Proteus Steinmetz, a pioneering German-American electrical engineer and mathematician renowned for his foundational work in alternating current (AC) power systems.
-
C.
Proteus
Proteus is an experimental high-altitude, long-endurance aircraft designed by Scaled Composites for telecommunications, reconnaissance, and research missions.
-
D.
Proteus
Proteus is one of Neptune’s largest irregularly shaped moons, known for its dark surface and heavily cratered, ancient terrain.
-
E.
Aien Aristeuein
Aien Aristeuein is the ancient Greek motto of the University of St Andrews, traditionally translated as "Ever to Excel" and expressing a commitment to continual striving for excellence.
- F. None of above. chosen
Statements (41)
| Predicate | Object |
|---|---|
| instanceOf |
AI research project
ⓘ
Allen Institute for Artificial Intelligence project ⓘ natural language processing system ⓘ question-answering system ⓘ |
| affiliation | Allen Institute for Artificial Intelligence ⓘ |
| basedIn |
Seattle
ⓘ
Washington ⓘ |
| country |
United States
ⓘ
linked to:
United States of America
|
| developer | Allen Institute for Artificial Intelligence ⓘ |
| evaluationMethod |
multiple-choice science questions
ⓘ
standardized test benchmarks ⓘ |
| field |
artificial intelligence
ⓘ
automated reasoning ⓘ natural language processing ⓘ question answering ⓘ |
| focusesOnLanguage | English ⓘ |
| goal |
achieve high performance on standardized science exams
ⓘ
advance AI systems that can pass school science tests ⓘ demonstrate machine reasoning over science knowledge ⓘ |
| hasComponent |
knowledge resources
ⓘ
question answering models ⓘ reasoning modules ⓘ |
| notableResult |
high scores on 8th-grade science exams
ⓘ
progress toward passing standardized science tests ⓘ |
| organization | Allen Institute for Artificial Intelligence ⓘ |
| publicationType | research papers ⓘ |
| researchFocus |
answering standardized science exam questions
ⓘ
explainable question answering ⓘ machine reading comprehension for science ⓘ multi-hop reasoning ⓘ reasoning about science exam questions ⓘ |
| shortName | Aristo ⓘ |
| taskDomain |
elementary school science exams
ⓘ
middle school science exams ⓘ standardized science tests ⓘ |
| uses |
information retrieval
ⓘ
knowledge bases ⓘ natural language understanding ⓘ neural networks ⓘ symbolic reasoning ⓘ |
| website | https://allenai.org/aristo ⓘ |
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 project Description of subject: The Aristo project is an AI research initiative by the Allen Institute for Artificial Intelligence focused on building systems that can answer and reason about standardized science exam questions.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.