Classifier Instance:

Anchor text: artifacted
Target Entity: Compression_artifact
Preceding Context: The resulting compression ratio can be varied according to need by being more or less aggressive in the divisors used in the quantization phase. Ten to one compression usually results in an image that cannot be distinguished by eye from the original. 100 to one compression is usually possible, but will look distinctly
Succeeding Context: compared to the original. The appropriate level of compression depends on the use to which the image will be put.
Paragraph Title: Compression ratio and artifacts
Source Page: JPEG

Ground Truth Types:

|---wordnet_entity_100001740
|  |---wordnet_artifact_100021939
|  |  |---wordnet_artifact_100021939_rest

Predicted Types:

TypeConfidenceDecision
wordnet_artifact_1000219390.22851211962063367 1
wordnet_instrumentality_103575240-1.2346914952292376 0
wordnet_structure_104341686-1.680158673979672 0
wordnet_facility_103315023-1.4149977225810282 0
wordnet_creation_103129123-1.0118563078273972 0
wordnet_article_100022903-0.7755988564006714 0
wordnet_commodity_103076708-0.8456622065249427 0
wordnet_way_104564698-0.9504771515498455 0
wordnet_covering_103122748-0.8228169225109718 0
wordnet_event_100029378-1.4950426223673925 0
wordnet_organization_108008335-2.158540484763126 0
wordnet_person_100007846-1.6085750521771545 0
yagoGeoEntity-1.7123301583980024 0
|---wordnet_entity_100001740
|  |---wordnet_artifact_100021939
|  |  |---wordnet_instrumentality_103575240
|  |  |---wordnet_structure_104341686
|  |  |---wordnet_facility_103315023
|  |  |---wordnet_creation_103129123
|  |  |---wordnet_article_100022903
|  |  |---wordnet_commodity_103076708
|  |  |---wordnet_way_104564698
|  |  |---wordnet_covering_103122748
|  |---wordnet_event_100029378
|  |---wordnet_organization_108008335
|  |---wordnet_person_100007846
|  |---yagoGeoEntity
|  |  |---wordnet_structure_104341686
|  |  |---wordnet_facility_103315023
|  |  |---wordnet_way_104564698