A developer is building a system to identify and categorize entities like names of people, organizations, and locations within a sentence. They use a pre-trained transformer model that processes an entire input sentence at once. For each token in the sentence, the model produces a corresponding output vector. The developer's current design takes only the output vector corresponding to a special initial token (often called [CLS]) and feeds it into a single classification layer to predict all the entity tags for the entire sentence simultaneously.

Which statement best analyzes the flaw in this design for this specific task?

A system is designed to identify named entities (like persons, organizations, or locations) in the sentence 'Jane works at Acme Corp'. The system uses a transformer-based model that processes the entire sentence and generates a contextualized vector representation for each token ('Jane', 'works', 'at', 'Acme', 'Corp'). To determine that 'Acme' is part of an organization name, what specific information should be passed to the final classification layer?

You are building a system to identify named entities in text using a transformer-based model. Arrange the following steps in the correct logical order to describe how the system processes an input sentence to produce entity tags.