Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their effectiveness in low-resource languages remains underexplored, particularly in complex tasks such as end-to-end Entity Linking (EL), which requires both mention detection and disambiguation against a knowledge base (KB). In earlier work, we introduced IndEL — the first end-to-end EL benchmark dataset for the Indonesian language — covering both a general domain (news) and a specific domain (religious text from the Indonesian translation of the Quran), and evaluated four traditional end-to-end EL systems on this dataset. In this study, we propose ELEVATE-ID, a comprehensive evaluation framework for assessing LLM performance on end-to-end EL in Indonesian. The framework evaluates LLMs under both zero-shot and fine-tuned conditions, using multilingual and Indonesian monolingual models, with Wikidata as the target KB. Our experiments include performance benchmarking, generalization analysis across domains, and systematic error analysis. Results show that GPT-4 and GPT-3.5 achieve the highest accuracy in zero-shot and fine-tuned settings, respectively. However, even fine-tuned GPT-3.5 underperforms compared to DBpedia Spotlight — the weakest of the traditional model baselines — in the general domain. Interestingly, GPT-3.5 outperforms Babelfy in the specific domain. Generalization analysis indicates that fine-tuned GPT-3.5 adapts more effectively to cross-domain and mixed-domain scenarios. Error analysis uncovers persistent challenges that hinder LLM performance: difficulties with non-complete mentions, acronym disambiguation, and full-name recognition in formal contexts. These issues point to limitations in mention boundary detection and contextual grounding. Indonesian-pretrained LLMs, Komodo and Merak, reveal core weaknesses: template leakage and entity hallucination, respectively—underscoring architectural and training limitations in low-resource end-to-end EL. 1

Entity and relation linking critically impact the accuracy of knowledge graph question answering (KGQA), often limiting the performance of downstream tasks like query generation. While recent advances in large language models (LLMs) offer promising solutions, their role in linking remains underexplored. This work studies how different linking strategies – including both traditional and LLM-based approaches– affect the quality of generated KG queries. We design multiple linking pipelines and use their output to guide structured query construction. Our study not only evaluates linking accuracy, but also the end-to-end impact on query generation. Our experiments show that LLM-based linkers significantly outperform non-LLM methods, particularly in recall. Moreover, we find that high recall—even at the cost of precision—can lead to better overall performance, as LLMs are resilient to input noise. These findings highlight the importance of recall-oriented linking in modern KGQA pipelines.

Entity typing in knowledge graphs (KGs) aims to infer missing types of entities and might be considered one of the most significant tasks of knowledge graph construction since type information is highly relevant for querying, quality assurance, and KG applications. While supervised learning approaches for entity typing have been proposed, they require large amounts of (manually) labeled data, which can be expensive to obtain. In this paper, we propose a novel approach for KG entity typing that leverages semi-supervised learning from massive unlabeled data. Our approach follows a teacher-student paradigm that allows combining a small amount of labeled data with a large amount of unlabeled data to boost performance. We conduct several experiments on two benchmarking datasets (FB15k-ET and YAGO43k-ET). Our results demonstrate the effectiveness of our approach in improving entity typing in KGs. Given type information for only 1% of entities, our approach ASSET predicts missing types with a F1-score of 0.47 and 0.64 on the datasets FB15k-ET and YAGO43k-ET, respectively, outperforming supervised baselines.

Existing technologies employ different machine learning approachesto predict disasters from historical environmental data. However,for short-term disasters (e.g., earthquakes), historical data alonehas a limited prediction capability. In this work, we consider so-cial media as a supplementary source of knowledge in additionto historical environmental data. Further, we build a joint modelthat learns from disaster-related tweets and environmental data toimprove prediction. We propose the combination of semantically-enriched word embedding to represent entities in tweets with theirsemantics representations computed with the traditionalword2vec.Our experiments show that our proposed approach outperformsthe accuracy of state-of-the-art models in disaster prediction