addEntityDetails — Add named-entity tags to tokenized documents.
addEntityDetails(documents) adds named-entity metadata to a RunMat tokenizedDocument compatibility object. Use tokenDetails to view the resulting Entity column.
Syntax
updatedDocuments = addEntityDetails(documents)
updatedDocuments = addEntityDetails(documents,Name,Value)Inputs
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
documents | Any | Yes | — | tokenizedDocument object. |
NameValue | Any | Variadic | — | Name-value options: RetokenizeMethod, DiscardKnownValues, Model. |
Returns
| Name | Type | Description |
|---|---|---|
updatedDocuments | Any | Updated tokenized document object. |
Errors
| Identifier | When | Message |
|---|---|---|
RunMat:addEntityDetails:InvalidInput | Input is not a supported tokenizedDocument object or option form. | addEntityDetails: invalid input |
How addEntityDetails works
documentsmust be a RunMattokenizedDocumentobject.addEntityDetails(documents, Name, Value)supportsRetokenizeMethod,DiscardKnownValues, andModelname-value pairs.RetokenizeMethoddefaults to"entity", which merges simple adjacent entity tokens such as multiword locations. Use"none"to keep existing tokens.DiscardKnownValuesdefaults tofalse, so existing known entity details are preserved while missing or empty entries are filled.DiscardKnownValues,truerecomputes every stored tag and ignores malformed stored entity details.Model,"auto"selects RunMat's built-in deterministic compatibility tagger. CustomhmmEntityModelinputs remain tracked as broader Text Analytics model infrastructure.addEntityDetailsensures sentence and part-of-speech details exist first, then updates part-of-speech details for recognized entities to"proper-noun".- RunMat tags English and German tokens with deterministic compatibility rules for
person,location,organization,other, andnon-entity. - If an existing tokenizedDocument object already carries Japanese or Korean language metadata, RunMat accepts the language and uses conservative token-class-aware fallback tags. Public Japanese/Korean tokenizedDocument construction and MeCab-backed entity models remain tracked.
- Exact MathWorks statistical entity-model parity remains tracked as broader Text Analytics work.
GPU memory and residency
addEntityDetails updates host tokenizedDocument metadata and has no provider kernel.
Examples
Add Entity Details
documents = tokenizedDocument("Mary uses MATLAB at MathWorks.");
documents = addEntityDetails(documents);
tdetails = tokenDetails(documents)Expected output:
`tdetails.Entity` contains tags such as `"person"`, `"organization"`, `"other"`, and `"non-entity"`.Keep Existing Tokens
documents = addEntityDetails(documents, "RetokenizeMethod", "none")Expected output:
`documents` receives entity details without the entity retokenization pass.Recompute Entity Details
documents = addEntityDetails(documents, "DiscardKnownValues", true)Expected output:
`documents` has refreshed entity details.Using addEntityDetails with coding agents
Open a RunMat example with live inputs, then ask the agent to explain how addEntityDetails changes the result.
Run a small addEntityDetails example, explain the result, then change one input and compare the output.
FAQ
Does addEntityDetails use a full entity model?⌄
No. This compatibility slice uses deterministic English and German rules and records exact MathWorks model parity as remaining Text Analytics work.
Does addEntityDetails execute on the GPU?⌄
No. It updates host tokenizedDocument metadata.
Related Strings functions
Text Analytics
addDependencyDetails · addLemmaDetails · addPartOfSpeechDetails · addSentenceDetails · addTypeDetails · bagOfNgrams · bagOfWords · cosineSimilarity · doc2sequence · encode · extractFileText · extractHTMLText · fastTextWordEmbedding · findElement · getAttribute · htmlTree · ind2word · isVocabularyWord · normalizeWords · readWordEmbedding · removeLongWords · removeShortWords · removeStopWords · removeWords · stopWords · tokenDetails · tokenizedDocument · trainWordEmbedding · vaderSentimentScores · vec2word · word2ind · word2vec · wordEncoding · writeWordEmbedding
Transform
append · deblank · erase · eraseBetween · erasePunctuation · eraseURLs · extractAfter · extractBefore · extractBetween · insertAfter · insertBefore · join · lower · pad · replace · replaceBetween · reverse · split · splitlines · strcat · strip · strjoin · strjust · strrep · strsplit · strtrim · upper
Core
blanks · char · compose · convertCharsToStrings · convertContainedStringsToChars · convertStringsToChars · genvarname · int2str · isletter · isspace · isStringScalar · isstrprop · mat2str · native2unicode · newline · num2str · sprintf · sscanf · str2double · str2num · strcmp · strcmpi · string · string.empty · strings · strlength · strncmp · strncmpi · strtok · unicode2native
Search
contains · endsWith · matches · startsWith · strfind
Pattern
digitsPattern · lettersPattern · pattern · regexpPattern · textBoundary · wildcardPattern
Open-source implementation
Unlike proprietary runtimes, every RunMat function is open-source. Read exactly how addEntityDetails is executed, line by line, in Rust.
- View the source for addEntityDetails in Rust on GitHub
- Learn how the RunMat runtime works
- Found a bug? Open an issue with a minimal reproduction.
About RunMat
RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.
- RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
- Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.