@inproceedings{kovalchuk-etal-2026-schema,
title = "Schema-Guided Extraction of Interaction Knowledge Bases from Narrative Text: A Folktale Case Study",
author = "Kovalchuk, Sergey and
Ugleva, Anastasia and
Kubryak, Oleg",
editor = "Kalo, Jan-Christoph and
Nakashole, Ndapa and
Razniewski, Simon and
Suchanek, Fabian M. and
Vlachos, Andreas and
McCallum, Andrew",
booktitle = "Proceedings of the 11th Workshop on Automated Knowledge Base Construction ({AKBC} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.akbc-1.19/",
pages = "261--283",
ISBN = "979-8-89176-464-4",
abstract = "We present MAGIC, a six-dimensional framework for extracting structured knowledge bases of hero and magic entity interactions from narrative texts of folktales and fairytales: each interaction between a story{'}s protagonist and a magical helper, villain, or object is decomposed along trigger modality, actor profile and agency balance, interaction mechanics, outcome valence, narrative function, and narrative position. We build an LLM-based extraction pipeline and apply it to a corpus of 1306 folktales collected from around the world, then show the schema supports rich structural analysis: unsupervised clustering over the extracted features recovers five recurring, readily nameable interaction archetypes {--} invoked and unsolicited helpers, a morally tested gatekeeper, a hero-controlled magic object, and an adversarial obstacle {--} that are stable across the three full-corpus extraction models (0.95 mean cluster-centroid similarity) and cut across both tale type and regional tradition rather than reproducing existing typological catalogues. We further characterize the schema{'}s reliability under LLM extraction (inter-model, not against a human gold standard): parse success and schema-conformance rates, a decomposition of extraction drift into field-confusion versus vocabulary-incompleteness failure modes, and cross-model field-level agreement, which varies substantially across the six dimensions and is sensitive to how many tales are compared across models. Despite this field-level variability, the archetype-level structure remains stable, suggesting that knowledge bases built from LLM extraction should be evaluated at the level of the downstream structure they support."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kovalchuk-etal-2026-schema">
<titleInfo>
<title>Schema-Guided Extraction of Interaction Knowledge Bases from Narrative Text: A Folktale Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Kovalchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Ugleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Kubryak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ndapa</namePart>
<namePart type="family">Nakashole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Razniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Suchanek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-464-4</identifier>
</relatedItem>
<abstract>We present MAGIC, a six-dimensional framework for extracting structured knowledge bases of hero and magic entity interactions from narrative texts of folktales and fairytales: each interaction between a story’s protagonist and a magical helper, villain, or object is decomposed along trigger modality, actor profile and agency balance, interaction mechanics, outcome valence, narrative function, and narrative position. We build an LLM-based extraction pipeline and apply it to a corpus of 1306 folktales collected from around the world, then show the schema supports rich structural analysis: unsupervised clustering over the extracted features recovers five recurring, readily nameable interaction archetypes – invoked and unsolicited helpers, a morally tested gatekeeper, a hero-controlled magic object, and an adversarial obstacle – that are stable across the three full-corpus extraction models (0.95 mean cluster-centroid similarity) and cut across both tale type and regional tradition rather than reproducing existing typological catalogues. We further characterize the schema’s reliability under LLM extraction (inter-model, not against a human gold standard): parse success and schema-conformance rates, a decomposition of extraction drift into field-confusion versus vocabulary-incompleteness failure modes, and cross-model field-level agreement, which varies substantially across the six dimensions and is sensitive to how many tales are compared across models. Despite this field-level variability, the archetype-level structure remains stable, suggesting that knowledge bases built from LLM extraction should be evaluated at the level of the downstream structure they support.</abstract>
<identifier type="citekey">kovalchuk-etal-2026-schema</identifier>
<location>
<url>https://aclanthology.org/2026.akbc-1.19/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>261</start>
<end>283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Schema-Guided Extraction of Interaction Knowledge Bases from Narrative Text: A Folktale Case Study
%A Kovalchuk, Sergey
%A Ugleva, Anastasia
%A Kubryak, Oleg
%Y Kalo, Jan-Christoph
%Y Nakashole, Ndapa
%Y Razniewski, Simon
%Y Suchanek, Fabian M.
%Y Vlachos, Andreas
%Y McCallum, Andrew
%S Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-464-4
%F kovalchuk-etal-2026-schema
%X We present MAGIC, a six-dimensional framework for extracting structured knowledge bases of hero and magic entity interactions from narrative texts of folktales and fairytales: each interaction between a story’s protagonist and a magical helper, villain, or object is decomposed along trigger modality, actor profile and agency balance, interaction mechanics, outcome valence, narrative function, and narrative position. We build an LLM-based extraction pipeline and apply it to a corpus of 1306 folktales collected from around the world, then show the schema supports rich structural analysis: unsupervised clustering over the extracted features recovers five recurring, readily nameable interaction archetypes – invoked and unsolicited helpers, a morally tested gatekeeper, a hero-controlled magic object, and an adversarial obstacle – that are stable across the three full-corpus extraction models (0.95 mean cluster-centroid similarity) and cut across both tale type and regional tradition rather than reproducing existing typological catalogues. We further characterize the schema’s reliability under LLM extraction (inter-model, not against a human gold standard): parse success and schema-conformance rates, a decomposition of extraction drift into field-confusion versus vocabulary-incompleteness failure modes, and cross-model field-level agreement, which varies substantially across the six dimensions and is sensitive to how many tales are compared across models. Despite this field-level variability, the archetype-level structure remains stable, suggesting that knowledge bases built from LLM extraction should be evaluated at the level of the downstream structure they support.
%U https://aclanthology.org/2026.akbc-1.19/
%P 261-283
Markdown (Informal)
[Schema-Guided Extraction of Interaction Knowledge Bases from Narrative Text: A Folktale Case Study](https://aclanthology.org/2026.akbc-1.19/) (Kovalchuk et al., AKBC 2026)
ACL