When many utterances differ only by airport names or codes, you don't want to list them all. A Pattern.any entity acts as a placeholder for free-form input inside patterns, allowing the model to accept any word/phrase in that slot. Machine-learning entities require lots of labeled utterances. List entities work for fixed sets (e.g., specific known airport codes), but this scenario implies dynamic airport data. Regex entities are for structured formats (like postal codes). The answer: A Reference: Pattern.any entities in Language Understanding