Sustainability disclosure standards (e.g., GRI, SASB, TCFD, IFRS S2) are comprehensive yet lengthy, terminology-dense, and highly cross-referential, hindering structured analysis and downstream use. We present SSKG Hub (Sustainability Standards Knowledge Graph Hub), a research prototype and interactive web platform that transforms standards into auditable knowledge graphs (KGs) through an LLM-centered, expert-guided pipeline. The system integrates automatic standard identification, configurable chunking, standard-specific prompting, robust triple parsing, and provenance-aware Neo4j storage with fine-grained audit metadata. LLM extraction produces a provenance-linked Draft KG, which is reviewed, curated, and formally promoted to a Certified KG through meta-expert adjudication. A role-based governance framework covering read-only guest access, expert review and CRUD operations, meta-expert certification, and administrative oversight ensures traceability and accountability across draft and certified states. Beyond graph exploration and triple-level evidence tracing, SSKG Hub supports cross-KG fusion, KG-driven tasks, and dedicated modules for insights and curated resources. We validate the platform through a comprehensive expert-led KG review case study that demonstrates end-to-end curation and quality assurance. The web application is publicly available at www.sskg-hub.com.
Figures & tables
Figure 1: System overview of SSKG Hub. Sustainability standards PDFs (e.g., GRI, SASB, IFRS S2, TCFD) are processed via text extraction (PyMuPDF), LLM-based identification and chunking, and standard-specific prompting. Qwen-Max extracts normalized (subject, predicate, object) triples with aligned provenance, forming a provenance-aware Draft KG stored in Neo4j with audit metadata. Through expert review and meta-expert certification, validated triples are promoted to a Certified KG . On top of this graph core, SSKG Hub supports catalog management, interactive graph exploration with evidence tracing, triple inspection, cross-KGs fusion, downstream tasks (e.g., KGQA, reasoning paths), analytics, and immutable audit logging under role-based governance.
Figure 2: SSKG Hub UI highlights. Left: (1) standard-specific extraction setup, where users upload a sustainability standards PDF, verify the detected standard family, and inspect tailored prompt templates; (2) real-time ingestion monitoring with chunk-level progress and model transparency; and (3) a structured ingestion summary reporting document metadata and graph statistics. Right: (1) provenance-backed verification that links each triple to its source page and evidence span, with editable CRUD operations on selected (subject, predicate, object) triples; (2) an overall graph overview with zoom controls; (3) an interactive KG canvas for navigation, filtering, and structural exploration; and (4) a side panel displaying the original PDF with search and export utilities for traceable validation.
Category
Representative capabilities
Standards KGQA
QA over a selected SSKG: entity matching, concise answers, reasoning paths, subgraph view.
Reasoning & path analysis
Bounded-hop reasoning and source–target path search with stepwise paths and mini-graph view.
Comparative & anomaly analysis
Multi-entity comparison (fact counts, shared/unique predicates) and prompt-based anomaly detection.
Knowledge graph construction turns text, tables, images, and databases into structured entities and relationships that machines can query and reason over.
The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided framework for knowledge graph (KG) construction. Our framework utilizes specialized agents for document understanding, information extraction, ontology conformance, and entity linking. First, an LLM extracts factual knowledge in the form of triples with explicit textual evidence from research papers. Then the triplets undergo a multistage verification process to ground the triplets in the ontology. By enforcing schema constraints and requiring evidence in the form of text fragments, we ensure the data is both semantically consistent and traceable. In an agreement study over 1,000 extracted triplets, Gemini-2.5-flash achieves Cohen's κ scores of 0.640--0.700 against three human annotators, matching the human--human agreement range of 0.616--0.689. We applied this framework to 2,000 scientific publications and construct a novel, ontology-grounded KG for climate science with 133,990 nodes and 755,308 relations; of the 23,327 triplets that the publications contribute after validation, 98.96% are judged correct. The pipeline code and KG is publicly available https://github.com/aayushacharya/climatekg.
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small graph samples, rather than task-specific fine-tuning? We integrate VoID descriptions and ShEx schemas into a retrieval-augmented generation (RAG) pipeline and ablate KG-derived context on the SciQA benchmark. Our best configuration -- combining ShEx schemas, retrieved triples, and example question-query pairs -- reaches an exact match of 0.419 on execution results without any LLM fine-tuning. We further find that lexical metrics such as F1 poorly predict query correctness, and that larger general-purpose LLMs can outperform smaller code-specialized ones once given sufficient context. Second, we ask how to generate the structured metadata that this method relies on from very large KGs, where KG metadata generation becomes computationally intractable. We introduce a predicate-coverage-aware parallel graph sampling strategy that preserves structural diversity while remaining computationally tractable. On OpenCitations Meta and GESIS, it retains high predicate coverage with minimal triple loss and reduces runtime by over 80x; on ORKG, sampling is not just faster but the only tractable path to obtain complete metadata. Together, these results show that structured schema context and lightweight prompting can substantially reduce reliance on fine-tuning for scalable conversational access to KGs, though closing the remaining gap to fully fine-tuned approaches will likely require reducing dependence on curated question-query exemplars -- whether through synthetic generation or an execution-feedback-driven approach -- and validating these findings beyond a single benchmark.
We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM). GPTKB 2.0 contains 38.4M triples over 1.6M canonical entities, together with 207.6K consolidated relations and 66K consolidated classes. Unlike prior LLM-derived knowledge bases that largely identify entities by surface strings, GPTKB 2.0 performs context-guided disambiguation during recursive KB construction, separating homonyms and merging synonymous mentions as facts are elicited. The demo makes this process inspectable: users can browse entities, follow links across the KB, and audit the provenance of individual facts, including surface forms, candidate matches, source triples, and disambiguation decisions. The interface further supports structured SPARQL queries, natural-language questions translated to SPARQL, and entity linking from user-provided text to canonical GPTKB 2.0 entries. GPTKB 2.0 is available at https://gptkb.org/, with the full KB downloadable for offline use.
Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski
ScaDS.AI Dresden/Leipzig & TU Dresden, Germany · VNU University of Engineering and Technology, Hanoi, Vietnam