diff --git a/website/docs/api/cython-structs.md b/website/docs/api/cython-structs.md
index 1d3139a96..0e427a8d5 100644
--- a/website/docs/api/cython-structs.md
+++ b/website/docs/api/cython-structs.md
@@ -172,7 +172,7 @@ struct.
 | `prefix`    | <Abbr title="uint64_t">`attr_t`</Abbr>  | Length-N substring from the start of the lexeme. Defaults to `N=1`.                                                        |
 | `suffix`    | <Abbr title="uint64_t">`attr_t`</Abbr>  | Length-N substring from the end of the lexeme. Defaults to `N=3`.                                                          |
 | `cluster`   | <Abbr title="uint64_t">`attr_t`</Abbr>  | Brown cluster ID.                                                                                                          |
-| `prob`      | `float`                                 | Smoothed log probability estimate of the lexeme's type.                                                                    |
+| `prob`      | `float`                                 | Smoothed log probability estimate of the lexeme's word type (context-independent entry in the vocabulary).                 |
 | `sentiment` | `float`                                 | A scalar value indicating positivity or negativity.                                                                        |
 
 ### Lexeme.get_struct_attr {#lexeme_get_struct_attr tag="staticmethod, nogil" source="spacy/lexeme.pxd"}
diff --git a/website/docs/api/lexeme.md b/website/docs/api/lexeme.md
index d5e5c54b8..5ec2aaf0c 100644
--- a/website/docs/api/lexeme.md
+++ b/website/docs/api/lexeme.md
@@ -161,6 +161,6 @@ The L2 norm of the lexeme's vector representation.
 | `is_stop`                                    | bool    | Is the lexeme part of a "stop list"?                                                                         |
 | `lang`                                       | int     | Language of the parent vocabulary.                                                                           |
 | `lang_`                                      | unicode | Language of the parent vocabulary.                                                                           |
-| `prob`                                       | float   | Smoothed log probability estimate of the lexeme's type.                                                      |
+| `prob`                                       | float   | Smoothed log probability estimate of the lexeme's word type (context-independent entry in the vocabulary).   |
 | `cluster`                                    | int     | Brown cluster ID.                                                                                            |
 | `sentiment`                                  | float   | A scalar value indicating the positivity or negativity of the lexeme.                                        |
diff --git a/website/docs/api/token.md b/website/docs/api/token.md
index a4607b186..2085a02c6 100644
--- a/website/docs/api/token.md
+++ b/website/docs/api/token.md
@@ -465,7 +465,7 @@ The L2 norm of the token's vector representation.
 | `dep_`                                       | unicode      | Syntactic dependency relation.                                                                                                                                                                                                |
 | `lang`                                       | int          | Language of the parent document's vocabulary.                                                                                                                                                                                 |
 | `lang_`                                      | unicode      | Language of the parent document's vocabulary.                                                                                                                                                                                 |
-| `prob`                                       | float        | Smoothed log probability estimate of token's type.                                                                                                                                                                            |
+| `prob`                                       | float        | Smoothed log probability estimate of token's word type (context-independent entry in the vocabulary).                                                                                                                         |
 | `idx`                                        | int          | The character offset of the token within the parent document.                                                                                                                                                                 |
 | `sentiment`                                  | float        | A scalar value indicating the positivity or negativity of the token.                                                                                                                                                          |
 | `lex_id`                                     | int          | Sequential ID of the token's lexical type.                                                                                                                                                                                    |