I have this input from a chat:

“Set an alarm for 7:00 am and play a song by Caparezza on Spotify.”

The input may contain multiple action to do on back-end.
I want to divide a text based on the action to do, and the text can be very complex, so I want to use NLP to get the Entity, and I want also to categorize the text based on intent, just as I have shown below with an example.

I prefer to use Spacy, and I don’t know if is enough to get all the context for complex text categorization that is not based on pattern.

Based on the input, the output that I want to obtain is:

Output:

[
    {
    quote: "Set an alarm for 7:00 am",
    intent: set_alarm
    },
    {
    quote: "play song by Caparezza on spotify",
        intent: "play_song"
    }
]

I tried with sentecizer from spacy, but I want something to train for more reliability.