Skip to content

Information exraction output

The information extraction resource returns a JSON object with this format:

{
    "success": Boolean success flag,
    "data": {
        "content": analyzed text,
        "language": language code,
        "version": technology version info,
        "extractions": []
    }
}

For the description of the contents, language and version properties, see output overview.

Each item of the extractions array represents an extraction record, for example:

"extractions": [
    {
        "namespace": "project01",
        "template": "RELATIONS",
        "fields": [
            {
                "name": "DISEASE",
                "value": "Diabetes",
                "positions": [
                    {
                        "start": 1621,
                        "end": 1629
                    }
                ]
            },
            {
                "name": "DISEASE2",
                "value": "COVID-19",
                "positions": [
                    {
                        "start": 1673,
                        "end": 1684
                    }
                ]
            },
            {
                "name": "RELATION",
                "value": "TR_RISK_FACTOR",
                "positions": [
                    {
                        "start": 1642,
                        "end": 1656
                    }
                ]
            }
        ]
    }
]
  • namespace is the name of the software module carrying out information extraction inside the text intelligence engine.
  • template is the name of the record's template
  • fields is the array of record's fields.

Each item of the fields array represents an extracted field, where:

  • name is the field's name.
  • value is the field's value.
  • positions is an array containing the extracted field's positions.

Info

You can find more information about templates and fields in the Studio documentation.