rows {
  options {
    physical_type: PHYSICAL_STREAM_TYPE_QUADS
    max_name_table_size: 128
    max_prefix_table_size: 16
    max_datatype_table_size: 16
    logical_type: LOGICAL_STREAM_TYPE_DATASETS
    version: 2
  }
}
rows {
  prefix {
    value: "https://w3id.org/np/"
  }
}
rows {
  name {
    value: "RAVx7L-tHl-XheF8kQ7DFRsxgAXPVzXrgK7z_DxuViXWE"
  }
}
rows {
  namespace {
    name: "this"
    value {
      prefix_id: 1
    }
  }
}
rows {
  prefix {
    value: "https://w3id.org/np/RAVx7L-tHl-XheF8kQ7DFRsxgAXPVzXrgK7z_DxuViXWE/"
  }
}
rows {
  name {
  }
}
rows {
  namespace {
    name: "sub"
    value {
      prefix_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.nanopub.org/nschema#"
  }
}
rows {
  namespace {
    name: "np"
    value {
      prefix_id: 3
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://purl.org/dc/terms/"
  }
}
rows {
  namespace {
    name: "dct"
    value {
      prefix_id: 4
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://purl.org/pav/"
  }
}
rows {
  namespace {
    name: "pav"
    value {
      prefix_id: 5
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
  }
}
rows {
  namespace {
    name: "rdf"
    value {
      prefix_id: 6
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/2002/07/owl#"
  }
}
rows {
  namespace {
    name: "owl"
    value {
      prefix_id: 7
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/2004/03/trix/rdfg-1/"
  }
}
rows {
  namespace {
    name: "rdfg"
    value {
      prefix_id: 8
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://purl.org/dc/elements/1.1/"
  }
}
rows {
  namespace {
    name: "dce"
    value {
      prefix_id: 9
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/2001/XMLSchema#"
  }
}
rows {
  namespace {
    name: "xsd"
    value {
      prefix_id: 10
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/2000/01/rdf-schema#"
  }
}
rows {
  namespace {
    name: "rdfs"
    value {
      prefix_id: 11
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://www.w3.org/ns/prov#"
  }
}
rows {
  namespace {
    name: "prov"
    value {
      prefix_id: 12
      name_id: 2
    }
  }
}
rows {
  prefix {
    value: "http://purl.org/nanopub/x/"
  }
}
rows {
  namespace {
    name: "npx"
    value {
      prefix_id: 13
      name_id: 2
    }
  }
}
rows {
  name {
    value: "hasAssertion"
  }
}
rows {
  name {
    value: "assertion"
  }
}
rows {
  name {
    value: "Head"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 1
      name_id: 1
    }
    p_iri {
      prefix_id: 3
      name_id: 3
    }
    o_iri {
      prefix_id: 2
    }
    g_iri {
    }
  }
}
rows {
  name {
    value: "hasProvenance"
  }
}
rows {
  name {
    value: "provenance"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 3
    }
    o_iri {
      prefix_id: 2
    }
  }
}
rows {
  name {
    value: "hasPublicationInfo"
  }
}
rows {
  name {
    value: "pubinfo"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 3
    }
    o_iri {
      prefix_id: 2
    }
  }
}
rows {
  name {
    value: "type"
  }
}
rows {
  name {
    value: "Nanopublication"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 6
    }
    o_iri {
      prefix_id: 3
    }
  }
}
rows {
  prefix {
    value: "https://doi.org/10.48550/"
  }
}
rows {
  name {
    value: "arXiv.2511.11017"
  }
}
rows {
  name {
    value: "title"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 14
    }
    p_iri {
      prefix_id: 4
    }
    o_literal {
      lex: "AI Agent-Driven Framework for Automated Product Knowledge Graph Construction in E-Commerce"
    }
    g_iri {
      prefix_id: 2
      name_id: 4
    }
  }
}
rows {
  prefix {
    value: "http://purl.org/spar/cito/"
  }
}
rows {
  name {
    value: "describes"
  }
}
rows {
  prefix {
    value: "https://neverblink.eu/ontologies/llm-kg/methods#"
  }
}
rows {
  name {
    value: "AiAgentDrivenFramework"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 15
      name_id: 14
    }
    o_iri {
      prefix_id: 16
    }
  }
}
rows {
  name {
    value: "discusses"
  }
}
rows {
  name {
    value: "BiEtAlCodeKGC"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 15
    }
    o_iri {
      prefix_id: 16
    }
  }
}
rows {
  name {
    value: "CuiEtAlKGICL"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "GrapherMethod"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "KommineniEtAlKGPipeline"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "LairgiEtAliText2KG"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "NingEtAlFactualExtraction"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "XieEtAlPromptKG"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "XuEtAlProductKGEmbedding"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "YaoEtAlKGLLM"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "ZhangEtAlEDCFramework"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "ZhuEtAlAutoKG"
  }
}
rows {
  quad {
    o_iri {
    }
  }
}
rows {
  name {
    value: "Entity"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 12
      name_id: 28
    }
  }
}
rows {
  name {
    value: "subject"
  }
}
rows {
  prefix {
    id: 5
    value: "https://neverblink.eu/ontologies/llm-kg/categories#"
  }
}
rows {
  name {
    value: "LLMAugmentedKGConstruction"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 15
    }
    p_iri {
      prefix_id: 4
      name_id: 29
    }
    o_iri {
      prefix_id: 5
    }
  }
}
rows {
  prefix {
    id: 7
    value: "http://purl.org/spar/fabio/"
  }
}
rows {
  name {
    value: "Workflow"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  name {
    value: "comment"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This framework uses LLM-powered agents to automate the entire process of Knowledge Graph construction. It involves three main stages: ontology creation and expansion (entity/relation discovery), ontology refinement (schema improvement), and knowledge graph population (instance extraction) from unstructured product descriptions, directly addressing KG construction tasks."
    }
  }
}
rows {
  name {
    value: "label"
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "AI Agent-Driven Framework"
    }
  }
}
rows {
  prefix {
    value: "https://neverblink.eu/ontologies/llm-kg/"
  }
}
rows {
  name {
    value: "hasTopCategory"
  }
}
rows {
  prefix {
    value: "https://neverblink.eu/ontologies/llm-kg/top-categories#"
  }
}
rows {
  name {
    value: "LLMAugmentedKG"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 8
    }
    o_iri {
      prefix_id: 9
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 17
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "Presented by Bi et al., CodeKGC is a method that employs code LLMs and schema-aware prompts for generative KG tasks, enhanced by rationale-based generation."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "CodeKGC"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 18
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "Proposed by Cui et al., KG-ICL is a method that combines in-context learning with a prompt graph and unified tokenization to achieve strong generalization across various KG tasks."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "KG-ICL"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 19
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "Grapher is discussed as a method that generates end-to-end KGs by dividing tasks into entity and relation extraction using pre-trained Language Models."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "Grapher"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 20
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This method is mentioned as a prior LLM-based pipeline that aims to minimize human intervention in KG construction by incorporating competency-question-based ontology generation and LLM-driven evaluation."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "Kommineni et al.\'s Pipeline"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 21
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "Proposed by Lairgi et al., this method is presented as a zero-shot, plug-and-play system for distilling unstructured input into KGs with minimal post-processing."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "iText2KG"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 22
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This method by Ning et al. explores factual knowledge extraction for KGs via prompt templates and parameter tuning to improve accuracy."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "Ning et al.\'s Factual Knowledge Extraction"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 23
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "Xie et al. introduced PromptKG, a toolkit designed to integrate prompt-learning methods for various Knowledge Graph applications."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "PromptKG"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 24
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This embedding method, proposed by Xu et al., is tailored for product KGs and uses multimodal data to enhance KG completion and recommendation tasks."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "Xu et al.\'s Embedding Method"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 25
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This method, presented by Yao et al., utilizes entity/relation prompts for triple classification and relation prediction, focusing on Knowledge Graph completion tasks."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "KG-LLM"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 26
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This method, proposed by Zhang et al., is discussed as a prior LLM-based approach for automated KG construction, which separates open information extraction, schema creation, and canonicalization."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "EDC Framework"
    }
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 16
      name_id: 27
    }
    p_iri {
      prefix_id: 6
      name_id: 10
    }
    o_iri {
      prefix_id: 7
      name_id: 31
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
    }
    o_literal {
      lex: "This framework, introduced by Zhu et al., is discussed as a multi-agent system that combines LLMs with external data for KG construction."
    }
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "AutoKG Framework"
    }
  }
}
rows {
  name {
    value: "wasAttributedTo"
  }
}
rows {
  name {
    value: "agent"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 2
      name_id: 4
    }
    p_iri {
      prefix_id: 12
      name_id: 36
    }
    o_iri {
      prefix_id: 8
    }
    g_iri {
      prefix_id: 2
      name_id: 7
    }
  }
}
rows {
  name {
    value: "wasDerivedFrom"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 12
      name_id: 38
    }
    o_iri {
      prefix_id: 14
      name_id: 12
    }
  }
}
rows {
  name {
    value: "created"
  }
}
rows {
  datatype {
    value: "http://www.w3.org/2001/XMLSchema#dateTime"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 1
      name_id: 1
    }
    p_iri {
      prefix_id: 4
      name_id: 39
    }
    o_literal {
      lex: "2026-03-13T16:02:03.618Z"
      datatype: 1
    }
    g_iri {
      prefix_id: 2
      name_id: 9
    }
  }
}
rows {
  name {
    value: "creator"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 4
      name_id: 40
    }
    o_iri {
      prefix_id: 8
      name_id: 37
    }
  }
}
rows {
  name {
    value: "hasNanopubType"
  }
}
rows {
  name {
    value: "PaperAssessmentResult"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 13
      name_id: 41
    }
    o_iri {
      prefix_id: 8
    }
  }
}
rows {
  name {
    value: "supersedes"
  }
}
rows {
  name {
    value: "RANj-wpb535FlB8eM5KHVx-XFfUEYhWRWquqtlRjwEmD4"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 13
    }
    o_iri {
      prefix_id: 1
    }
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 11
      name_id: 33
    }
    o_literal {
      lex: "LLM-KG assessment for paper 10.48550/arXiv.2511.11017"
    }
  }
}
rows {
  name {
    value: "sig"
  }
}
rows {
  name {
    value: "hasAlgorithm"
  }
}
rows {
  quad {
    s_iri {
      prefix_id: 2
      name_id: 45
    }
    p_iri {
      prefix_id: 13
    }
    o_literal {
      lex: "RSA"
    }
  }
}
rows {
  name {
    value: "hasPublicKey"
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB"
    }
  }
}
rows {
  name {
    value: "hasSignature"
  }
}
rows {
  quad {
    p_iri {
    }
    o_literal {
      lex: "iLSElcgqqBsWTLtic7yrdoX2HgsuT/lKI7xDXW5jloh4uxRGPdY72/D+LdNE8CNXSiWOI5ndpSWJhachzVbWHxLqG/f1ihRAQTBOQrQ2U49UvOZN5SXBLqMzk0inB3uXMduZBmiSk9EhOpn+KY/DNcZOHnMtpE0gXLkOxmVdvtIlpQzr2QsLAdj02YMEC01ndKNcmyXL8wvcUrTnmHreZjxjeaAzElGlCmRV0+yVNisxrrgm0Ur+Y5YwDmxMtRob2HFlJkjc1l/mkeMOe5IRHEp87HyMppCQhl0WW4lR9XkHfdbYrafIummDmzfrvg1R+JnTnILVuC7HVin5rFAswA=="
    }
  }
}
rows {
  name {
    value: "hasSignatureTarget"
  }
}
rows {
  quad {
    p_iri {
    }
    o_iri {
      prefix_id: 1
      name_id: 1
    }
  }
}
rows {
  name {
    value: "signedBy"
  }
}
rows {
  quad {
    p_iri {
      prefix_id: 13
      name_id: 50
    }
    o_iri {
      prefix_id: 8
      name_id: 37
    }
  }
}