<![CDATA[ITS Online Publication (POMITS) is a publication journal for ITS undergraduate students. Many articles are published in it, and they are often needed as reference material for other student research. The search process is still based on title, abstract, author's name, and keywords. The data is still entered manually by the author. This process allows the selection of less appropriate keywords. So an effort is needed so that the choice of these keywords can be more precise and represent the article.The purpose of this research is to identify keywords in articles automatically. These keywords are distinguished into the software used, methods, and other representative keywords. With this identification, article searches can return more precise search results. This problem can be solved by using Named Entity Recognition (NER). However, the Indonesian language NER model owned by SpaCy is still not available, so it is necessary to develop the NER model.This study identifies each keyword annotation in POMITS content into metadata by detecting named entities in the form of software, methods, and representative keywords using the NER model. The NER annotation results are stored as triplet pairs in the Apache Jena Fuseki triple store. Furthermore, the triple store can answer searches about software, methods, and keywords. Based on the test results, the system successfully detects NER entities and saves annotations as triplet pairs on Apache Jena Fuseki. Keywords identification produce an average value of 84.76% precision and 63.59% recall. ]]>
