Entity Reference

The Einstein NER (beta) API supports normalization for some entities. Normalized data is returned in the normalizedData array. The type and format of the data depends on the type of entity.

CREDIT CARD

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `credit_card`	2.0
`issuer`	string	Credit card issuer. Valid values: American Express Diner’s Club Discover Japan Credit Bureau Maestro Card Mastercard Visa other	2.0
`value`	string	Value of the normalized data	2.0

With the exception of the ja locale, credit card numbers are detected regardless of the locale provided in the request. When the request document is passed with ja locale, we support numbers written in full-width characters.

Examples

1"probability": 1.0,
2"label": "CREDIT-CARD-NUMBER",
3"token": "5555-5555-5555-4444",
4"span": {
5    "start": 0,
6    "end": 19
7},
8"normalizedData": [
9    {
10        "value": "5555555555554444",
11        "issuer": "Mastercard", # credit card issuer
12        "type": "credit_card"
13    }
14]

Though we identify valid credit card number formats (using Luhn’s algorithm test), we do not post process the value to determine whether a number is a real-world credit card.

Note

DATETIME

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token. `range`—Object contains from and to objects that represent the start value and end value for the token.	2.0
`unit`	string	Unit of measurement for the token value. Valid values: `day` `hour` `minute` `month` `quarter` `second`</li `week` `year` The unit returned by the API is determined by the unit in the token. For example, if the token is “between today and tomorrow” the unit is day.	2.0
`value`	string	Value of the normalized data.	2.0

This entity can sometimes overlap with the DURATION and NUMBER entities.

Examples

1{
2    "token": "...",
3    "label": "DATETIME",
4    "probability": 0.9787207,
5    "normalizedData": [
6        {
7            "type": "value",
8            "unit": "hour",
9            "value": "2020-02-03T17:00:00.000-08:00" // 5pm
10        },
11        ... or ...
12        {
13            "type": "range", // between 4pm and 5pm
14            "from": {
15                "type": "value",
16                "unit": "hour",
17                "value": "2020-02-03T16:00:00.000-08:00"
18            },
19            "to": {
20                "type": "value",
21                "unit": "hour",
22                "value": "2020-02-03T17:00:00.000-08:00"
23            }
24        }
25    ]
26}

1{
2    "probabilities": [
3        {
4            "probability": 0.84189475,
5            "label": "DATETIME",
6            "token": "between today and tomorrow",
7            "span": {
8                "start": 22,
9                "end": 48
10            },
11            "normalizedData": [
12                {
13                    "from": {
14                        "value": "2020-08-10T00:00:00.000-07:00", // Today's date
15                        "unit": "day",
16                        "type": "value"
17                    },
18                    "to": {
19                        "value": "2020-08-12T00:00:00.000-07:00", // Tomorrow's date
20                        "unit": "day",
21                        "type": "value"
22                    },
23                    "type": "range"
24                }
25            ]
26        }
27    ],
28    "object": "predictresponse"
29}

DURATION

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Unit of measurement for the token value. Valid values: `second`—Number of seconds in the duration.	2.0
`value`	string	Value of the normalized data.	2.0

This entity can sometimes overlap with the DATETIME and NUMBER entities.

Example

1{
2    "token": "3 hours",
3    "label": "DURATION",
4    "probability": 0.9125207,
5    "normalizedData": [
6        {
7            "type": "value",
8            "value": "10800",
9            "unit": "second"
10        }
11    ]
12}

EMAIL

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Empty for the EMAIL entity type.	2.0
`value`	string	Value of the normalized data.	2.0

The API recognizes email addresses in these two formats.

info at salesforce dot com
info@salesforce.com

Example

1{
2    "probabilities": [
3        {
4            "probability": 1,
5            "label": "EMAIL",
6            "token": "info at salesforce dot com",
7            "span": {
8                "start": 0,
9                "end": 26
10            },
11            "normalizedData": [
12                {
13                    "value": "info@salesforce.com",
14                    "unit": "",
15                    "type": "value"
16                }
17            ]
18        }
19    ],
20    "object": "predictresponse"
21}

LOCATION

Supports normalization: No

Example

1{
2    "token": "London",
3    "label": "LOCATION",
4    "probability": 0.9787207,
5    "normalizedData": [],
6    "span": {
7        ...
8    }
9}

MONEY

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Unit of measurement for the token value. Valid values: `EUR`—Euro `GBP`—British pound stering `RUB`—Russian ruble `USD`—United States dollar	2.0
`value`	string	Value of the normalized data. For money, it’s the numeric value of the specified currency.	2.0

Example

1{
2    "probabilities": [
3        {
4            "probability": 0.95074475,
5            "label": "MONEY",
6            "token": "five dollars",
7            "span": {
8                "start": 21,
9                "end": 33
10            },
11            "normalizedData": [
12                {
13                    "value": "5",
14                    "unit": "USD",
15                    "type": "value"
16                }
17            ]
18        }
19    ],
20    "object": "predictresponse"
21}

NUMBER

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Empty for the NUMBER entity type.	2.0
`value`	string	Value of the normalized data.	2.0

Example

1{
2    "probabilities": [
3        {
4            "probability": 1,
5            "label": "NUMBER",
6            "token": "Three thousand",
7            "span": {
8                "start": 0,
9                "end": 14
10            },
11            "normalizedData": [
12                {
13                    "value": "3000",
14                    "unit": "",
15                    "type": "value"
16                }
17            ]
18        }
19    ],
20    "object": "predictresponse"
21}

ORGANIZATION

Supports normalization: No

Example

1{
2    "probability": 0.9469566,
3    "label": "ORGANIZATION",
4    "token": "Salesforce",
5    "span": {
6        "start": 25,
7        "end": 35
8    },
9    "normalizedData": []
10}

PERCENT

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token. `range`—Object contains from and to objects that represent the start value and end value for the token.	2.0
`unit`	string	Empty for the PERCENT entity type.	2.0
`value`	string	Value of the normalized data.	2.0

The normalized value is the percent divided by 100. For example, 50 percent is 0.5. Recognizes percentages in these formats:

50%
50 percent

Example

1// Single value example
2{
3  "token": "150%",
4  "label": "PERCENT",
5  "probability": 0.9787207,
6  "normalizedData": [
7    {
8      "type": "value",
9      "unit": "",
10      "value": "1.5"
11    }
12  ]
13}
14
15// Range value example
16{
17  "probability": 0.99382097,
18  "label": "PERCENT",
19  "token": "40-50%",
20  "span": {
21    "start": 26,
22    "end": 32
23  },
24  "normalizedData": [
25    {
26      "from": {
27        "value": "0.4",
28        "unit": "",
29        "type": "value"
30      },
31      "to": {
32        "value": "0.5",
33        "unit": "",
34        "type": "value"
35      },
36      "type": "range"
37    }
38  ]
39}

PERSON

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`firstName`	string	Text identified as the person’s first name.	2.0
`lastName`	string	Text identified as the person’s last name.	2.0
`middleName`	string	Text identified as the person’s middle name.	2.0
`salutation`	string	Empty for the PERSON entity type.	2.0
`suffix`	string	Text identified as the person’s suffix such as Jr., Sr., and so on.	2.0
`type`	string	Normalization type. Valid values: `person`	2.0

Titles are not detected. For example, for the string Dr. Jim Blimpish only Jim and Blimpish are detected.

Note

Example

1"probability": 0.99966216,
2  "label": "PERSON",
3  "token": "Marc Benioff",
4  "span": {
5    "start": 0,
6    "end": 12
7  },
8  "normalizedData": [
9    {
10      "firstName": "Marc",
11      "lastName": "Benioff",
12      "middleName": "",
13      "suffix": "",
14      "salutation": "",
15      "type": "person"
16    }
17  ]

PHONE-NUMBER

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Empty for the PHONE-NUMBER entity type.	2.0
`value`	string	Value of the normalized data.	2.0

Example

1{
2    "probability": 1,
3    "label": "PHONE-NUMBER",
4    "token": "408-123-4455",
5    "span": {
6        "start": 37,
7        "end": 49
8    },
9    "normalizedData": [
10        {
11            "value": "4081234455",
12            "unit": "",
13            "type": "value"
14        }
15    ]
16}

URL

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `value`—Object contains the normalized value for the token.	2.0
`unit`	string	Empty for the URL entity type.	2.0
`value`	string	Value of the normalized data.	2.0

1{
2    "probabilities": [
3        {
4            "probability": 1,
5            "label": "URL",
6            "token": "https://developer.salesforce.com/signup.",
7            "span": {
8                "start": 58,
9                "end": 98
10            },
11            "normalizedData": [
12                {
13                    "value": "https://developer.salesforce.com/signup.",
14                    "unit": "",
15                    "type": "value"
16                }
17            ]
18        }
19    ],
20    "object": "predictresponse"
21}

SOCIAL SECURITY NUMBER

Supports normalization: Yes

Normalization fields

Name	Type	Description	Available Version
`type`	string	Normalization type. Valid values: `social_security`	2.0
`value`	string	Value of the normalized data.	2.0

EXAMPLE

1"probability": 1.0,
2"label": "SOCIAL-SECURITY-NUMBER",
3"token": "135-24-2244",
4"span": {
5   "start": 0,
6   "end": 11
7},
8"normalizedData": [
9   {
10      "value": "135242244",
11      "type": "social_security"
12   }
13]

Though we identify valid social security number formats we do not post process the value to determine whether a number is a real-world social security number.

Note