Skip to content

TYPE attribute overview

Basic syntax

The TYPE attribute matches the type of tokens, that is their word class or their entity type.

The syntax is:

TYPE(type1[, type2, ...])


  • TYPE is the attribute name and must be written in uppercase.
  • type# refers to a predefined value chosen between the language word classes—for example nouns, verbs, adjectives—and the types of entity the disambiguator can recognize—for example person names, dates, addresses.

Available world classes and entity types are listed below.

Word classes

Word class Description
ADJ Adjective
ART Article
AUX Auxiliary verb
ADV Adverb
CON Conjunction
NOU Noun
NPR Proper noun
PNT Punctuation mark
PRE Preposition
PRO Pronoun
PRT Particle
VER Verb


The PRT attribute is available for German and French only.

Entity types

Label Description Example
ADR Street address Who lived at 221B Baker Street?
ANM Animal Felix is an anthropomorphic black cat.
BLD Building While in London I attended a concert at the Royal Albert Hall.
COM Company, business Tesla Inc. sold 10% of its Bitcoin holdings.
DAT Date Napoleon died on May 5, 1821.
DEV Device My new Galaxy smartphone has seven cameras.
DOC Document I appeal to the Geneva Convention!
ENT Generic entity I have five minutes left.
EVN Event Felice Gimondi won the Tour de France in 1965.
FDD Food, beverage Frank likes to drink Guinness beer.
GEA Physical geographic feature I crossed the Mississipi river with my boat.
GEO Administrative geographic area Alaska is the least densely populated state in the United States.
GEX Extended geography The astronauts have landed on Mars.
HOU Hours The eclipse reached its peak at 3pm.
LEN Legal entity Of course I pay the FICA tax.
MAI Email address For any questions do not hesitate to write to [email protected].
MEA Measure The chest is five feet wide and 40 inches tall.
MMD Mass media I read it in the Guardian.
MON Money I sold half of my stocks and made six hundred thousand dollars.
NPH Person Hakeem Olajuwon dunked effortlessly.
ORG Organization, institution, society Now they threaten to quit the United Nations if they are not heard.
PCT Percentage The richest 10% of adults in the world own 85% of global wealth.
PHO Phone number For poor database design, call (214) 748-3647.
PPH Physical phenomena The COVID-19 infection is slowing down.
PRD Product The Rolex Daytona is a wonderful watch.
VCL Vehicle A Ferrari 250 GTO was the most expensive car ever sold.
WEB Web address Find the best technical documentation at
WRK Work of human intelligence Grease is a funny musical romantic comedy.


Consider the following example:


The operand above matches two word classes: nouns (NOU) like cat and adjectives (ADJ) like strong.

The following operand, on the other hand:


matches entities of two types, dates (DAT) and addresses (ADR), when recognized in a text. See the topic about entity recognition for more information.


If used alone, the TYPE attribute, can be hyper generative, so it's advisable to use it in conjunction with other attributes.


You can specify sub-attributes. These are grammatical features of the token such as the gender and number of nouns, the tense of verbs, the type of adverbs, etc.

For example, this rule:


applied to this text:

Mary went to the sea with her children.

will match sea, a singular noun, but not children.

You can specify one or more sub-attributes. The syntax is:

type:subAttribute1[:subAttribute2 ...]

Available sub-attributes for each language are described on the following pages.

When you specify more sub-attributes, be sure they belong to different lists of features of the TYPE value. For example, this rule with a value of NOU:


has two sub-attributes:

If you specify two sub-attributes belonging to the same list of features of the TYPE value, like this other rule:


The last sub-attribute—overwriting the first one—will be considered. To be sure both sub-attributes belonging to the same list of features of the TYPE value are evaluated, write the rule like this:

        @REGULAR_VERBS[TYPE(VER:simple_past, VER:ed_form)]

The comma acts like an OR operand between the sub-attributes.