Lantner Named Entity Recognition

Movie Data Extraction from HTML

This tool specializes in extracting movie-related entities from HTML content. It uses a fine-tuned GLiNER 2.1 multilang model that was trained using automated labeling with GPT-4.1-nano to identify and extract movie information such as titles, years, runtime, ratings, genres, directors, cast, and plot details.

How to use: Enter a URL to a webpage containing movie information (e.g., IMDB, CSFD, etc.) and the tool will fetch the HTML and extract movie entities.

Examples: title, year, runtime, rating, genre, director, cast, plot

Processing...

Response: