Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.08597 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908950445686784 |
|---|---|
| author | Zhang, Wenxiao Liu, Yu sun, Qiang Ding, Yihao Li, Sirui Liu, Yanbing Hong, Jin B. Liu, Wei |
| author_facet | Zhang, Wenxiao Liu, Yu sun, Qiang Ding, Yihao Li, Sirui Liu, Yanbing Hong, Jin B. Liu, Wei |
| contents | Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce \textbf{STIndex}, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. \textbf{STIndex} integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, \textbf{STIndex} improves spatiotemporal entity extraction F1 by 4.37\% (GPT-4o-mini) and 3.60\% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System Zhang, Wenxiao Liu, Yu sun, Qiang Ding, Yihao Li, Sirui Liu, Yanbing Hong, Jin B. Liu, Wei Databases Artificial Intelligence Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce \textbf{STIndex}, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. \textbf{STIndex} integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, \textbf{STIndex} improves spatiotemporal entity extraction F1 by 4.37\% (GPT-4o-mini) and 3.60\% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard. |
| title | STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System |
| topic | Databases Artificial Intelligence |
| url | https://arxiv.org/abs/2604.08597 |