Performing the Entity Extraction

The goal of the Entity Extraction process is to find locations in the text which contain entity information. In other words, it tries to find occurrences of person names, locations, organizations, VAT numbers, etc.

The entity extraction finds entities in the set of documents located in the Documents folder of a Case Project. The Documents folder is a special predefined folder which contains all input documents for the entity extraction. This means that download bookmarks or import documents from local disk into the Document folder is a prerequisite for running the entity extraction process.

The Documents folder is marked with a special icon: $images_download\attachments\2588750\icon-documents-folder.png$ . Whenever the Documents folder shows a greater sign in front of its name, the entity extraction needs to run:

$images_download\attachments\2588750\documents-folder-marked-for-extraction.png$

You can run the entity extraction as follows:

In the Workspace Navigator view click on the case project containing the Documents folder which is not up-to-date.

$images_download\attachments\2588750\entity-extraction-00.png$

In the main menu click on Project > Build Extraction. The entity extraction starts to run, you can monitor the progress in the Progress View

$images_download\attachments\2588750\entity-extraction-01.png$

Alternatively, you can use the context menu to run the Entity Extraction. Right-click on the Documents folder in the Workspace Navigator view, then click Build Extraction. The entity extraction starts to run.

$images_download\attachments\2588750\entity-extraction-01-2.png$

As soon as the entity extraction has finished, the Documents folder is no longer marked with the > sign:

$images_download\attachments\2588750\documents-folder-extraction-up-to-date.png$