diff --git a/doc/tutorials/learning_to_rank.rst b/doc/tutorials/learning_to_rank.rst
index 74e52e156..4d2cbad4a 100644
--- a/doc/tutorials/learning_to_rank.rst
+++ b/doc/tutorials/learning_to_rank.rst
@@ -72,8 +72,11 @@ Please note that, as of writing, there's no learning-to-rank interface in scikit
 .. code-block:: python
 
   import pandas as pd
+
+  # `X`, `qid`, and `y` are from the previous snippet, they are all sorted by the `sorted_idx`.
   df = pd.DataFrame(X, columns=[str(i) for i in range(X.shape[1])])
-  df["qid"] = qid[sorted_idx]
+  df["qid"] = qid
+
   ranker.fit(df, y)  # No need to pass qid as a separate argument
 
   from sklearn.model_selection import StratifiedGroupKFold, cross_val_score