WIP.
diff --git a/built-in-entity-parser.html b/built-in-entity-parser.html
index 54caad6..b2f0b95 100644
--- a/built-in-entity-parser.html
+++ b/built-in-entity-parser.html
@@ -233,9 +233,11 @@
would require pre-existing marked up data sets and extensive training. For each semantic element you can either provide a
set of synonyms to match on or specify a piece of code that would be responsible for detecting that named
entity (discussed below). A synonym can have one or more individual words. Note that element's ID is its
- implicit synonym so that even if no additional synonyms are defined at least one synonym always exists. Note
- also that synonym matching is performed on <em>normalized</em> and <em>stemmatized</em> forms of both
- a synonym and user input.
+ implicit synonym so that even if no additional synonyms are defined at least one synonym always exists.
+ Note also that synonym matching is performed on <em>normalized</em> and <em>stemmatized</em> forms of both
+ a synonym and user input on first phase and if first attempt is not successful, it tries to match <em>stemmatized</em> forms
+ of synonyms with <em>stemmatized</em> forms of user input which were <em>lemmatized</em> preliminarily.
+ This approach allows to provide more accurate matching and doesn't force users to prepare synonyms in initial words form. .
</p>
<p>
