@inproceedings{chepurova-etal-2026-wikontic,
title = "Wikontic: Constructing {W}ikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models",
author = "Chepurova, Alla and
Bulatov, Aydar and
Burtsev, Mikhail and
Kuratov, Yuri",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.388/",
pages = "8304--8319",
ISBN = "979-8-89176-380-7",
abstract = "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 \textit{Wikontic}, a multi-stage pipeline that constructs KGs from open-domain texts 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$\times$ fewer than AriGraph and $<$1/20 of GraphRAG.The proposed pipeline improves the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs. Wikontic is available at https://github.com/screemix/Wikontic."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chepurova-etal-2026-wikontic">
<titleInfo>
<title>Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alla</namePart>
<namePart type="family">Chepurova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aydar</namePart>
<namePart type="family">Bulatov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Burtsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Kuratov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>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 texts 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\times fewer than AriGraph and <1/20 of GraphRAG.The proposed pipeline improves the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs. Wikontic is available at https://github.com/screemix/Wikontic.</abstract>
<identifier type="citekey">chepurova-etal-2026-wikontic</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.388/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>8304</start>
<end>8319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
%A Chepurova, Alla
%A Bulatov, Aydar
%A Burtsev, Mikhail
%A Kuratov, Yuri
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F chepurova-etal-2026-wikontic
%X 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 texts 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\times fewer than AriGraph and <1/20 of GraphRAG.The proposed pipeline improves the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs. Wikontic is available at https://github.com/screemix/Wikontic.
%U https://aclanthology.org/2026.eacl-long.388/
%P 8304-8319
Markdown (Informal)
[Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models](https://aclanthology.org/2026.eacl-long.388/) (Chepurova et al., EACL 2026)
ACL