BART
E435868
BART is a sequence-to-sequence transformer model developed by Facebook AI for tasks like text generation, summarization, and translation.
All labels observed (1)
| Label | Occurrences |
|---|---|
| BART canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T4389193 — 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: BART Context triple: [Hugging Face Transformers, supportsModelType, BART]
-
A.
BART
BART (Bay Area Rapid Transit) is a major rapid transit system serving the San Francisco Bay Area, linking cities like San Francisco, Oakland, and Berkeley with surrounding suburbs and regional transit networks.
-
B.
BART Antioch–SFO+Millbrae line
The BART Antioch–SFO+Millbrae line is a Bay Area Rapid Transit service that runs between Antioch in the East Bay and San Francisco International Airport and Millbrae, connecting suburban communities with major regional transit hubs.
-
C.
BART Green Line
The BART Green Line is a Bay Area Rapid Transit service route that operates trains through the South Bay, including stops such as Berryessa/North San José station.
-
D.
BART Fremont line
The BART Fremont line is a Bay Area Rapid Transit route in the San Francisco Bay Area that historically extended service to the city of Fremont in southern Alameda County.
-
E.
San Francisco Muni
San Francisco Muni is the primary public transportation system in San Francisco, operating the city’s network of buses, light rail, historic streetcars, and cable cars.
- 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: BART Target entity description: BART is a sequence-to-sequence transformer model developed by Facebook AI for tasks like text generation, summarization, and translation.
-
A.
BART
BART (Bay Area Rapid Transit) is a major rapid transit system serving the San Francisco Bay Area, linking cities like San Francisco, Oakland, and Berkeley with surrounding suburbs and regional transit networks.
-
B.
BART Antioch–SFO+Millbrae line
The BART Antioch–SFO+Millbrae line is a Bay Area Rapid Transit service that runs between Antioch in the East Bay and San Francisco International Airport and Millbrae, connecting suburban communities with major regional transit hubs.
-
C.
BART Green Line
The BART Green Line is a Bay Area Rapid Transit service route that operates trains through the South Bay, including stops such as Berryessa/North San José station.
-
D.
BART Fremont line
The BART Fremont line is a Bay Area Rapid Transit route in the San Francisco Bay Area that historically extended service to the city of Fremont in southern Alameda County.
-
E.
San Francisco Muni
San Francisco Muni is the primary public transportation system in San Francisco, operating the city’s network of buses, light rail, historic streetcars, and cable cars.
- F. None of above. chosen
Statements (52)
| Predicate | Object |
|---|---|
| instanceOf |
denoising autoencoder
ⓘ
neural network architecture ⓘ sequence-to-sequence transformer model ⓘ |
| applicationDomain | natural language processing ⓘ |
| architectureType | encoder-decoder ⓘ |
| basedOn | Transformer architecture ⓘ |
| combinesIdeasFrom |
BERT
ⓘ
GPT ⓘ |
| developer |
FAIR
ⓘ
Facebook AI ⓘ
linked to:
Meta AI
Facebook AI Research ⓘ
linked to:
Meta AI
|
| hasComponent |
decoder
ⓘ
encoder ⓘ |
| hasVariant |
BART-base
ⓘ
BART-large ⓘ
linked to:
BART-large-XSum
BART-large-CNN ⓘ BART-large-XSum ⓘ MBART ⓘ
linked to:
mBART
|
| inputType | text ⓘ |
| introducedInPaper |
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
ⓘ
linked to:
mBART
|
| introducedYear | 2019 ⓘ |
| language | English ⓘ |
| license | MIT-like (via Fairseq, depending on distribution) ⓘ |
| openSourceImplementation |
Fairseq
ⓘ
Hugging Face Transformers ⓘ |
| optimizationAlgorithm | Adam ⓘ |
| outputType | text ⓘ |
| paperAuthors |
Abdelrahman Mohamed
ⓘ
Luke Zettlemoyer ⓘ Marjan Ghazvininejad ⓘ Mike Lewis ⓘ Naman Goyal ⓘ Omer Levy ⓘ Veselin Stoyanov ⓘ Yinhan Liu ⓘ |
| pretrained | true ⓘ |
| pretrainingStrategy | corrupt-then-reconstruct ⓘ |
| releasedBy |
Facebook AI
ⓘ
linked to:
Meta AI
|
| supportsTask |
abstractive summarization
ⓘ
dialogue generation ⓘ machine translation ⓘ sequence tagging ⓘ text classification ⓘ text generation ⓘ |
| trainingObjective |
denoising autoencoding
ⓘ
sequence-to-sequence language modeling ⓘ |
| usesNoiseType |
document rotation
ⓘ
sentence permutation ⓘ text infilling ⓘ token deletion ⓘ token masking ⓘ |
| usesSubwordTokenization | true ⓘ |
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: BART Description of subject: BART is a sequence-to-sequence transformer model developed by Facebook AI for tasks like text generation, summarization, and translation.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.