A framework for managing duplicate predicates in RKGs that covers detection, resolution, and prevention that combines automated similarity-based methods with human validation and is designed for integration into the lifecycle of evolving, crowdsourced RKGs.
Abstract
Research Knowledge Graphs (RKGs) enable the structured representation of scientific knowledge, but their weakly enforced schemas make them prone to inconsistencies, particularly in how predicates are defined and used. Duplicate predicates, i.e., distinct identifiers expressing the same or highly similar relationships, introduce semantic redundancy, hinder reuse, and reduce RKG quality. While prior work has addressed duplicate detection for downstream tasks such as query answering or schema alignment, predicate redundancy as a data quality challenge, remains underexplored, particularly in terms of resolution, prevention, and semi-automated curator support. In this paper, we propose a framework for managing duplicate predicates in RKGs that covers detection, resolution, and prevention. The framework combines automated similarity-based methods with human validation and is designed for integration into the lifecycle of evolving, crowdsourced RKGs. We implement the framework in the context of the Open Research Knowledge Graph (ORKG) by extending its existing curation dashboard SciKGDash with embedding-based clustering, interactive inspection, and resolution actions such as merging and deleting. We evaluate the framework on the ORKG, where clustering reveals that up to 30% of predicates are potentially redundant. The analysis also shows recurring modeling patterns that lead to predicate redundancy, user-induced duplication, inconsistent identifier usage, and a lack of standardization in predicate naming and usage. Our findings demonstrate that duplicate predicates arise from user behavior and interface design. Addressing this, requires combining automated methods with human-centered curation and preventive mechanisms. This work positions predicate redundancy as a central data quality challenge and provides a foundation for more systematic and proactive RKG curation.
Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connected but scattered across text, tables, and knowledge graphs. This raises a practical question: when these modalities disagree, how can we detect and explain the conflict? We study this problem as modality-level inconsistency detection. We first introduce a taxonomy of cross-modal knowledge inconsistencies, covering information granularity differences, direct conflicts, temporal changes, and KG incompleteness. We then present Kontrast, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies. Experiments on various Table-QA datasets show that cross-modal inconsistencies are common and informative. They reveal not only true knowledge conflicts, but also missing KG structure and temporal mismatches while being limited by Text-to-SPARQL errors and noise. Our analysis shows that text, tables, and KGs can complement and correct one another through systematic comparison. Kontrast provides a practical tool for large-scale knowledge auditing and establishes a benchmark for future work on cross-modal knowledge consistency. Code and data are available at https://github.com/ECLADATTA/KONTRAST.
: Entity Matching (EM) is a core challenge in data integration, requiring the identification of records that refer to the same real-world entity across heterogeneous sources. Practical experience shows that overall performance depends on end-to-end system design rather than isolated algorithms: candidate generation, threshold calibration, provenance tracking, consolidation policies, and iterative error analysis often determine effectiveness. Ontologies, knowledge graphs, and persistent identifiers provide semantic context and stable references, but introduce additional complexity in handling uncertainty and evolving representations. We present a Named Entity Management System (NEMS) that integrates entity lifecycle management with scalable matching in a unified workflow for knowledge graph creation. Instead of treating reconciliation as post-processing, NEMS embeds matching and validation during ingestion, combining attribute-level similarity with graph-structured and ontology-aware signals to guide merge decisions. By integrating canonical identifiers, provenance tracking, and configurable decision thresholds, NEMS enables conservative merging, incremental updates, and explainable outcomes. The architecture accommodates diverse matching paradigms while leveraging structural context, providing a robust foundation for scalable and consistent entity integration.
Andrea Leoni, Andrea Molinari, Simone Sandri· Proceedings of the 15th Inte...· 0 citations
This work proposes Explore-Construct-Verify (ECV), a three-stage framework for API KG construction using large language models (LLMs), which preserves LLMs’ ability to discover domain-specific knowledge while enabling efficient post-hoc validation.
Yanbang Sun, Qing Huang, Zhenchang Xing et al.· ACM Transactions on Software...· 0 citations
A novel, interpretable metric for intrinsic KG quality assessment that measures how closely an automatically extracted graph approximates an"ideal"graph capturing the key noun phrases, predicate relations, and basic linguistic phenomena such as negation expressed in the source text is proposed.
Nipun Misra, Vikranth Udandarao, Aanchal Gupta et al.· 0 citations
The rapid expansion of scientific publications has significantly increased the complexity of traditional literature review processes. While recent advances in AI-assisted screening reduce manual effort, they fail to provide an actionable organization of findings beyond thematic clustering. We propose an integrated pipeline that transforms raw bibliographic data into queryable Knowledge Graphs (KGs), combining: (1) automated collection via the OpenAlex API, (2) LLM-assisted screening, (3) hierarchical semantic clustering using state-of-the-art embeddings (Qwen3-Embedding-4B), and (4) multi-relational KG construction in Neo4j with GraphRAG. We validate this methodology on a corpus of 50 K articles on Artificial Intelligence from the computer science literature. Our hierarchical clustering identifies 7 macro-clusters and 117 microclusters with Fused Gromov-Wasserstein (FGW) coherence. The resulting KG integrates 34,200 nodes across 9 entity types, revealing temporal evolution patterns, cross-institutional collaborations, and foundational knowledge pillars through citation analysis.
Le Van Olivier, Dardouillet Pierre, Boutalbi Karima· Annual International Compute...· 0 citations
guided table retrieval is presented, a four-phase pipeline that combines deterministic grounding via hash-based predictors, structural exploration of join-graph reachability, LLM-powered disambiguation of sources and targets, and algorithmic merging into minimal, topologically ordered join trees.
Alekh Jindal, J. Pandey, C. Pavlopoulou et al.· 0 citations
