gives a dataset of information about entities, dates, quantities and other content-related elements found in text.


searches for cases of the type form.


searches for cases of types form1, form2,


includes the property props for each object in the dataset produced.

Details and Options

  • In TextContents[text,], text can be a string, a file with plain text represented by File[], a ContentObject expression or a list of these text objects.
  • TextContents[{text1,text2,},] gives cases for each texti.
  • Identification type form can be:
  • "type"any text content type (e.g. "Noun", "City")
    Entity[,]a specific entity of a text content type
  • form matching any of the formi
  • Containing[outer,inner]forms of type outer containing type inner
    Verbatim["string"]a specific string to be matched exactly
    patterna string pattern to be matched
    Automaticentities, dates, quantities and other content-related elements
  • Possible choices for the property prop include:
  • "String"string of the identified text (default)
    "Position"start and end position of the string in text
    "Probability"estimated probability that the identification is correct
    "Type"type of content (entity type, )
    "Interpretation"standard interpretation of the identified string
    "Snippet"a snippet around the identified string
    "HighlightedSnippet"a snippet with the identified string highlighted
    Allall the preceding properties
    {prop1,prop2,}a list of property specifications
  • The following options can be given:
  • AcceptanceThresholdAutomaticminimum probability to accept identification
    TargetDevice"CPU"whether CPU or GPU computation should be used for entity detection
    VerifyInterpretationFalsewhether interpretability should be verified


open allclose all

Basic Examples  (1)

Find entities in a text:

Only get the results for locations:

Only get the results for locations and quantities:

Get interpretations for all cases:

Get a specified set of properties for entities:

Options  (2)

AcceptanceThreshold  (1)

By default, all the detected entities have an estimated probability higher than 0.5:

Get only the entities that are highly probable to be correct by setting a high AcceptanceThreshold:

VerifyInterpretation  (1)

By default, some entities cannot be interpreted, either because they are not correct or because they are not yet in the knowledgebase:

Use VerifyInterpretation to filter out the entities that cannot be interpreted:

Properties & Relations  (1)

TextContents handles the same types as TextPosition and TextCases and always identifies the same substrings as these functions for a given type:

A dataset that is similar to the output of TextContents can be obtained using TextCases:

Neat Examples  (1)

Load the text of a Wikipedia page about the Moon:

Extract notable text contents from the page:

Visualize the frequency of content types found on the page:

Find potential notable persons identified on the page:

Interpret these persons as entities:

Visualize occupations of these persons:

Introduced in 2019