diff --git a/site/en/guide/intro_to_graphs.ipynb b/site/en/guide/intro_to_graphs.ipynb
index 153cc24d469..0392a160d55 100644
--- a/site/en/guide/intro_to_graphs.ipynb
+++ b/site/en/guide/intro_to_graphs.ipynb
@@ -340,7 +340,7 @@
       "source": [
         "### Polymorphism: one `Function`, many graphs\n",
         "\n",
-        "A `tf.Graph` is specialized to a specific type of inputs (for example, tensors with a specific [`dtype`](https://www.tensorflow.org/api_docs/python/tf/dtypes/DType) or objects with the same [`id()`](https://docs.python.org/3/library/functions.html#id])).\n",
+        "A `tf.Graph` is specialized to a specific type of inputs (for example, tensors with a specific [`dtype`](https://www.tensorflow.org/api_docs/python/tf/dtypes/DType) or objects with the same [`id()`](https://docs.python.org/3/library/functions.html#id)).\n",
         "\n",
         "Each time you invoke a `Function` with a set of arguments that can't be handled by any of its existing graphs (such as arguments with new `dtypes` or incompatible shapes), `Function` creates a new `tf.Graph` specialized to those new arguments. The type specification of a `tf.Graph`'s inputs is known as its **input signature** or just a **signature**. For more information regarding when a new `tf.Graph` is generated and how that can be controlled, go to the _Rules of tracing_ section of the [Better performance with `tf.function`](./function.ipynb) guide.\n",
         "\n",