Find instances of colors in a ContentObject:

Find quantities in a File:

Use Alternatives to match multiple types:

Find all sentences in a string that contain currency amounts:

Find all sentences in a string that contain countries:

Combine Alternatives and Containing to form highly structured queries:

Specify multiple return types:

Show all the available properties in an Association:

Create a dataset with the properties of several types of entities:

Get the geodetic positions of the locations occurring in a text:

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:

Using PerformanceGoal->"Speed" can help to have faster detection, at the cost of lower accuracy:

By default, some entities cannot be interpreted, either because they are not correct or because they are not yet in the knowledgebase. In these cases, a string is returned instead of an interpretation:

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

Word segmentation preserves syntactic elements such as email addresses, URLs, and Twitter handles:

All the non-whitespace characters are grabbed with forms "Word" and "Punctuation":

Sentence segmentation intelligently ignores acronyms and other misleading boundaries:

Return all words of a given part of speech:

Make a table of word clouds from parts of speech:

Find countries:

Return interpreted strings as Entity objects:

Find currency amounts in a Wikipedia article:

Convert to another currency: