Who Is the Story About? Protagonist Entity Recognition in News

TL;DR

This paper introduces Protagonist Entity Recognition (PER), a new task to identify key organizations driving news stories, and demonstrates that large language models can effectively perform this task at scale, improving narrative understanding.

Contribution

The paper proposes PER as a novel task for identifying narrative-driving entities in news and shows how LLMs can be used for scalable, high-quality annotation and inference.

Findings

LLMs can reliably identify protagonists in news articles.

Guided LLMs approximate human judgments of narrative importance.

PER enhances narrative-centered information extraction.

Abstract

News articles often reference numerous organizations, but traditional Named Entity Recognition (NER) treats all mentions equally, obscuring which entities genuinely drive the narrative. This limits downstream tasks that rely on understanding event salience, influence, or narrative focus. We introduce Protagonist Entity Recognition (PER), a task that identifies the organizations that anchor a news story and shape its main developments. To validate PER, we compare he predictions of Large Language Models (LLMs) against annotations from four expert annotators over a gold corpus, establishing both inter-annotator consistency and human-LLM agreement. Leveraging these findings, we use state-of-the-art LLMs to automatically label large-scale news collections through NER-guided prompting, generating scalable, high-quality supervision. We then evaluate whether other LLMs, given reduced context and without explicit candidate guidance, can still infer the correct protagonists. Our results demonstrate that PER is a feasible and meaningful extension to narrative-centered information extraction, and that guided LLMs can approximate human judgments of narrative importance at scale.