A named entity is a real-world object, such as persons, locations, organizations, products, etc., that can be denoted with a proper name. It can be abstract or have a physical existence. 

Examples of named entities include Barack Obama, New York City, Volkswagen Golf, or anything else that can be named. Named entities can simply be viewed as entity instances (e.g., New York City is an instance of a city).


Named Entity Recognition (NER) is a subtask of information extraction that seeks to locate and classify entities from unstructured texts into pre-defined categories such as personal names, locations, time expressions, and many more.

NER algorithms are state-of-the-art intelligence system that are capable of finding entities from raw data and can determine the category, to which the element belongs. In Practice, the system reads the sentence and highlights the important entity elements in the text. 






BotSupply supports 2 types of entities that you can use when building your bot: standard entities and custom entities.


Standard entities are pre-trained entities that are ready to be used. You will find the following standard entities in the platform:


  • @std-currency: Extracts currency value including the amount and the currency ("26 DKK" or "15 euros")

  • @std-date: Extracts date and time value including year, month, day, hours and minutes ("February 14, 15:00" or "tomorrow at 9 AM")

  • @std-distance: Extracts distance value including the amount and the unit ("3 km" or "7 feet 10 inches")

  • @std-duration: Extracts duration values including the amount and the time unit ("1 month" or "one hour and half")

  • @std-email: Extracts emails adresses ("adrew@company.com")

  • @std-numeral: Extracts numeral values ("33" or "thirty three")

  • @std-ordinal: Extracts ordinal values ("25th" or "twenty-fifth")

  • @std-quantity: Extracts quantity values including the amount and the unit ("0.002 kg" or "3/4 cup")

  • @std-temperature: Extracts temperature values ("-2°" or "98.6 degrees F")

  • @std-volume: Extracts volume values including the amount and the unit ("500mls" or "half a liter")

  • @std-url: Extracts URLs ("cnn.com/info" or "https://en.wikipedia.org/")

  • @std-phone-number: Extracts phone numbers ("+1 6507018887" or "(+1) 650-701-8887")

  • @std-name: Extracts name values including first name, middle name, or last name ("Daniel" or "Jane Daniel Doe")


Custom entities are entities that are defined by you. Using BotSupply you can train the bot to recognize any entity you want. For example you can train the bot to recognize the names of your products from conversations.