diff --git a/featuretools/computational_backends/calculate_feature_matrix.py b/featuretools/computational_backends/calculate_feature_matrix.py
index c0f03ac599..75f5dc6ae3 100644
--- a/featuretools/computational_backends/calculate_feature_matrix.py
+++ b/featuretools/computational_backends/calculate_feature_matrix.py
@@ -65,11 +65,9 @@ def calculate_feature_matrix(features, entityset=None, cutoff_time=None, instanc
             where the second index is the cutoff time (first is instance id).
             DataFrame will be sorted by (time, instance_id).
 
-        training_window (dict[str -> Timedelta] or Timedelta, optional):
-            Window or windows defining how much older than the cutoff time data
-            can be to be included when calculating the feature.  To specify
-            which entities to apply windows to, use a dictionary mapping entity
-            id -> Timedelta. If None, all older data is used.
+        training_window (Timedelta, optional):
+            Window defining how much older than the cutoff time data
+            can be to be included when calculating the feature. If None, all older data is used.
 
         approximate (Timedelta or str): Frequency to group instances with similar
             cutoff times by for features with costly calculations. For example,
@@ -398,11 +396,9 @@ def approximate_features(features, cutoff_time, window, entityset, backend,
 
         entityset (:class:`.EntitySet`): An already initialized entityset.
 
-        training_window (dict[str-> :class:`Timedelta`] or :class:`Timedelta`, optional):
-            Window or windows defining how much older than the cutoff time data
-            can be to be included when calculating the feature.  To specify
-            which entities to apply windows to, use a dictionary mapping entity
-            id -> Timedelta. If None, all older data is used.
+        training_window (`Timedelta`, optional):
+            Window defining how much older than the cutoff time data
+            can be to be included when calculating the feature. If None, all older data is used.
 
         profile (bool, optional): Enables profiling if True
 
diff --git a/featuretools/entityset/entity.py b/featuretools/entityset/entity.py
index acb09e09d8..b0b54eda77 100644
--- a/featuretools/entityset/entity.py
+++ b/featuretools/entityset/entity.py
@@ -392,7 +392,7 @@ def query_by_values(self, instance_vals, variable_id=None, columns=None,
             columns (list[str]) : Columns to return. Return all columns if None.
             time_last (pd.TimeStamp) : Query data up to and including this
                 time. Only applies if entity has a time index.
-            training_window (dict[str -> Timedelta] or Timedelta, optional):
+            training_window (Timedelta, optional):
                 Data older than time_last by more than this will be ignored
             return_sorted (bool) : Return instances in the same order as
                 the instance_vals are passed.
diff --git a/featuretools/synthesis/dfs.py b/featuretools/synthesis/dfs.py
index bbaa031c78..dacdf632d7 100644
--- a/featuretools/synthesis/dfs.py
+++ b/featuretools/synthesis/dfs.py
@@ -107,11 +107,9 @@ def dfs(entities=None,
             where the second index is the cutoff time (first is instance id).
             DataFrame will be sorted by (time, instance_id).
 
-        training_window (dict[str -> Timedelta] or Timedelta, optional):
-            Window or windows defining how much older than the cutoff time data
-            can be to be included when calculating the feature.  To specify
-            which entities to apply windows to, use a dictionary mapping an entity
-            id to Timedelta. If None, all older data is used.
+        training_window (Timedelta, optional):
+            Window defining how much older than the cutoff time data
+            can be to be included when calculating the feature. If None, all older data is used.
 
         approximate (Timedelta): Bucket size to group instances with similar
             cutoff times by for features with costly calculations. For example,