I鈥檓 surprised it hasn鈥檛 been mentioned yet, but those news headlines weren鈥檛 actually retrieved, but hallucinated; it does a great job looking real, and sometimes, by chance, they are.

Secondly, why bother using a language model for something that can be accomplished with logic?

Some online news media have created Application Programming Interfaces (APIs) to enable computer applications to request stories and information about their stories (metadata) from them. "Platform API power all the BBC's product areas - iPlayer, News, Sport, Weather, Children's Knowledge and Learning - as well as many external and partner products such as Youview." Global Newswires Services in 16 Languages. Rich with facts and context that speak to readers everywhere.

You can easily connect to any of these APIs and just simply return the JSON.I feel like this is like building a bridge out of twigs, next to an actual bridge.

If NLP is a critical component you should consider fine-tuning an entity extraction model. GPT will hallucinate and return broken/incorrectly structured JSON. A lot.