# Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

arXiv: https://arxiv.org/abs/2512.00590 · HTML: https://mlsanity.com/paper/2512.00590/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Builds on (most cited first, 17 of 17)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [Language Models are Open Knowledge Graphs](https://mlsanity.com/paper/2010.11967/) (2020)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [GenIE: Generative Information Extraction](https://mlsanity.com/paper/2112.08340/) (2021)
- [KGGen: Extracting Knowledge Graphs from Plain Text with Language Models](https://mlsanity.com/paper/2502.09956/) (2025)
- [GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models](https://mlsanity.com/paper/2406.14550/) (2024)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction](https://mlsanity.com/paper/2009.07503/) (2020)
- [HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs](https://mlsanity.com/paper/2406.06027/) (2024)
- [Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering](https://mlsanity.com/paper/2410.08085/) (2024)
- [Self-supervised Graph Masking Pre-training for Graph-to-Text Generation](https://mlsanity.com/paper/2210.10599/) (2022)

## Built on by (most cited first, 6 of 6)

- [Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering](https://mlsanity.com/paper/2605.27164/) (2026)
- [Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction](https://mlsanity.com/paper/2605.29168/) (2026)
- [RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM](https://mlsanity.com/paper/2607.11683/) (2026)
- [PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents](https://mlsanity.com/paper/2605.13481/) (2026)
- [OCC-RAG: Optimal Cognitive Core for Faithful Question Answering](https://mlsanity.com/paper/2606.00683/) (2026)
- [Co-Evolving Structured Knowledge and Reasoning in Language Models](https://mlsanity.com/paper/2608.26386/) (2026)

## Abstract (arXiv)

Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3× fewer than AriGraph and <1/20 of GraphRAG. The proposed pipeline enhances the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs.