Rosette API entity extraction service

Returns each entity extracted from the input. The response is a list of extracted entities. Each entity includes an entityId (Wikidata QID or temporary ID), mention (entity text in the input), normalized text (complete form of the entity in the input), and the count (number of mentions of entity in the input).

ros_entities(content, genre = NULL, language = NULL)

Arguments

content

either a URI or character vector of content to process

genre

document genre (optional)

language

Language: ISO 639-3 code (optional)

Examples

txt <- c("Bill Murray will appear in new Ghostbusters film: Dr. Peter Venkman was ",
         "spotted filming a cameo in Boston this… http://dlvr.it/BnsFfS")
txt <- paste0(txt, collapse="")
ros_entities(txt)
#> $entities
#>             type               mention            normalized count entityId
#> 1         PERSON           Bill Murray           Bill Murray     1   Q29250
#> 2          TITLE                   Dr.                   Dr.     1       T1
#> 3         PERSON         Peter Venkman         Peter Venkman     1 Q2483011
#> 4       LOCATION                Boston                Boston     1     Q100
#> 5 IDENTIFIER:URL http://dlvr.it/BnsFfS http://dlvr.it/BnsFfS     1       T4
#> 
#>