<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosengren-2026-eventsocratickg">
    <titleInfo>
        <title>EventSocraticKG: Event-Centric Knowledge Graph Construction for Narrative Retrieval-Augmented Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="family">Rosengren</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>Graph-based retrieval over book-length narrative text faces a choice at construction time. Merging every mention of a character into one node erases the temporal context that separates an early portrayal from a later one; keeping mentions apart scatters a character across disconnected per-chunk nodes and leaves the consolidation to query time. We present EventSocraticKG (esokg), which (i) makes events first-class nodes in a bipartite event–entity graph, (ii) extracts them from 5W1H question–answer pairs written for each chunk instead of from the chunk text, and (iii) merges mentions across chunks by their full description, with embeddings proposing candidates and an LLM confirming them. At query time esokg serves graph structure only, with no source chunks and no LLM call. On 332 long-form questions over five books (four pre-2000 novels and one post-cutoff novel), scored by an LLM judge and re-scored by two independent judges, esokg lies within half a point of an unmerged entity–event comparator and of a full-budget entity-centric method that spends roughly twice the per-query tokens, under all three judges. The post-cutoff book separates retrieval from recall: an LLM without retrieval collapses there while every retrieval method holds, but esokg trails both graph comparators, so part of its pooled standing reflects books the models already know. Its category profile, strongest on the consistency categories and weakest on Narrative and Thematic, is largely unchanged on that book. The price is a one-time build two to three times the comparators’. What it buys is a chunk-free query path in the low per-query cost regime and a merged graph on which character-chain, shared-event, and causal-chain queries are short graph walks that need no language model.</abstract>
    <identifier type="citekey">rosengren-2026-eventsocratickg</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.9/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>108</start>
            <end>127</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EventSocraticKG: Event-Centric Knowledge Graph Construction for Narrative Retrieval-Augmented Generation
%A Rosengren, William
%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 rosengren-2026-eventsocratickg
%X Graph-based retrieval over book-length narrative text faces a choice at construction time. Merging every mention of a character into one node erases the temporal context that separates an early portrayal from a later one; keeping mentions apart scatters a character across disconnected per-chunk nodes and leaves the consolidation to query time. We present EventSocraticKG (esokg), which (i) makes events first-class nodes in a bipartite event–entity graph, (ii) extracts them from 5W1H question–answer pairs written for each chunk instead of from the chunk text, and (iii) merges mentions across chunks by their full description, with embeddings proposing candidates and an LLM confirming them. At query time esokg serves graph structure only, with no source chunks and no LLM call. On 332 long-form questions over five books (four pre-2000 novels and one post-cutoff novel), scored by an LLM judge and re-scored by two independent judges, esokg lies within half a point of an unmerged entity–event comparator and of a full-budget entity-centric method that spends roughly twice the per-query tokens, under all three judges. The post-cutoff book separates retrieval from recall: an LLM without retrieval collapses there while every retrieval method holds, but esokg trails both graph comparators, so part of its pooled standing reflects books the models already know. Its category profile, strongest on the consistency categories and weakest on Narrative and Thematic, is largely unchanged on that book. The price is a one-time build two to three times the comparators’. What it buys is a chunk-free query path in the low per-query cost regime and a merged graph on which character-chain, shared-event, and causal-chain queries are short graph walks that need no language model.
%U https://aclanthology.org/2026.akbc-1.9/
%P 108-127

Markdown (Informal)

[EventSocraticKG: Event-Centric Knowledge Graph Construction for Narrative Retrieval-Augmented Generation](https://aclanthology.org/2026.akbc-1.9/) (Rosengren, AKBC 2026)

• EventSocraticKG: Event-Centric Knowledge Graph Construction for Narrative Retrieval-Augmented Generation (Rosengren, AKBC 2026)

ACL

• William Rosengren. 2026. EventSocraticKG: Event-Centric Knowledge Graph Construction for Narrative Retrieval-Augmented Generation. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 108–127, Budapest, Hungary. Association for Computational Linguistics.