Your goal is to decompose a time series into its components — trend, seasonality, and residuals — using the seasonal_decompose() function from statsmodels.

1. Load the built-in "flights" dataset from seaborn.
2. Extract the "passengers" column as your target time series.
3. Apply seasonal_decompose() with an additive model and a period of 12 (months).
4. Store the result in a variable called decomposition.
5. Plot the original series, trend, seasonal, and residual components.

seasonal_decompose(series, model="additive", period=12) automatically splits the time series into four parts:

• trend → long-term movement;
• seasonal → repeating patterns;
• resid → random noise;
• observed → original data.

Each component can be accessed with attributes like .trend, .seasonal, .resid.