{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ARWPRIEKMZUH4ADN2HYNHX43CK","short_pith_number":"pith:ARWPRIEK","schema_version":"1.0","canonical_sha256":"046cf8a08a66687e006dd1f0d3df9b12ae0f58515843e95d52b27e0039440850","source":{"kind":"arxiv","id":"2412.20942","version":1},"attestation_state":"computed","paper":{"title":"Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Helen Meng, Xiaohan Feng, Xixin Wu","submitted_at":"2024-12-30T13:36:05Z","abstract_excerpt":"We propose an ontology-grounded approach to Knowledge Graph (KG) construction using Large Language Models (LLMs) on a knowledge base. An ontology is authored by generating Competency Questions (CQ) on knowledge base to discover knowledge scope, extracting relations from CQs, and attempt to replace equivalent relations by their counterpart in Wikidata. To ensure consistency and interpretability in the resulting KG, we ground generation of KG with the authored ontology based on extracted relations. Evaluation on benchmark datasets demonstrates competitive performance in knowledge graph construct"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.20942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-30T13:36:05Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7bcd614fbcbcdffb34c0ff5f25b46522c6ceea381f715fa821aeb44365d770d8","abstract_canon_sha256":"83ca805d5ded8cbd6bc6c9e41efb86a6433ba7ae307a39a17a817360414881a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:25.126624Z","signature_b64":"g1Da6955zdSi1oW0n728eZSLR4ygCYkpDdOoGhRhMOuWrr1FTPFwtIx5NaYPLv+q+Xpz23wU6GqJxfbOEe7mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046cf8a08a66687e006dd1f0d3df9b12ae0f58515843e95d52b27e0039440850","last_reissued_at":"2026-07-05T09:55:25.126114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:25.126114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Helen Meng, Xiaohan Feng, Xixin Wu","submitted_at":"2024-12-30T13:36:05Z","abstract_excerpt":"We propose an ontology-grounded approach to Knowledge Graph (KG) construction using Large Language Models (LLMs) on a knowledge base. An ontology is authored by generating Competency Questions (CQ) on knowledge base to discover knowledge scope, extracting relations from CQs, and attempt to replace equivalent relations by their counterpart in Wikidata. To ensure consistency and interpretability in the resulting KG, we ground generation of KG with the authored ontology based on extracted relations. Evaluation on benchmark datasets demonstrates competitive performance in knowledge graph construct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20942","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.20942/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.20942","created_at":"2026-07-05T09:55:25.126170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20942v1","created_at":"2026-07-05T09:55:25.126170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20942","created_at":"2026-07-05T09:55:25.126170+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARWPRIEKMZUH","created_at":"2026-07-05T09:55:25.126170+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARWPRIEKMZUH4ADN","created_at":"2026-07-05T09:55:25.126170+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARWPRIEK","created_at":"2026-07-05T09:55:25.126170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02618","citing_title":"OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23090","citing_title":"Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20795","citing_title":"Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK","json":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK.json","graph_json":"https://pith.science/api/pith-number/ARWPRIEKMZUH4ADN2HYNHX43CK/graph.json","events_json":"https://pith.science/api/pith-number/ARWPRIEKMZUH4ADN2HYNHX43CK/events.json","paper":"https://pith.science/paper/ARWPRIEK"},"agent_actions":{"view_html":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK","download_json":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK.json","view_paper":"https://pith.science/paper/ARWPRIEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20942&json=true","fetch_graph":"https://pith.science/api/pith-number/ARWPRIEKMZUH4ADN2HYNHX43CK/graph.json","fetch_events":"https://pith.science/api/pith-number/ARWPRIEKMZUH4ADN2HYNHX43CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK/action/storage_attestation","attest_author":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK/action/author_attestation","sign_citation":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK/action/citation_signature","submit_replication":"https://pith.science/pith/ARWPRIEKMZUH4ADN2HYNHX43CK/action/replication_record"}},"created_at":"2026-07-05T09:55:25.126170+00:00","updated_at":"2026-07-05T09:55:25.126170+00:00"}