{"id":"W4407873161","doi":"10.2139/ssrn.5152241","title":"Context-Aware Entity-Relation Extraction Pipeline for Threat Intelligence Knowledge Graphs","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Pipeline (software); Context (archaeology); Computer science; Relation (database); Knowledge graph; Relationship extraction; Extraction (chemistry); Entity linking; Artificial intelligence; Data science; Knowledge management; Data mining; Knowledge base; Programming language; Geography; Chemistry; Chromatography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0182483,0.0003823036,0.0005981081,0.0009590777,0.0005626283,0.000747582,0.001927012,0.0003755648,0.0001618134],"category_scores_gemma":[0.002003427,0.0003239696,0.0006312668,0.0005925323,0.00009928931,0.0006627053,0.0007583573,0.003572703,0.0001796106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123808,"about_ca_system_score_gemma":0.003076649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779944,"about_ca_topic_score_gemma":0.009585654,"domain_scores_codex":[0.9942973,0.0005526175,0.00157933,0.0009228458,0.001039663,0.001608229],"domain_scores_gemma":[0.9955519,0.001245256,0.001128617,0.0008984431,0.001058267,0.0001174949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001064889,0.0001446864,0.0001029475,0.00004016223,0.0001589119,8.220547e-7,0.0002271053,0.000524519,0.000003501026,0.5263186,0.007237228,0.4651351],"study_design_scores_gemma":[0.0003174362,0.000102476,0.000104059,0.0001594758,0.000164304,0.00002198873,0.003874604,0.007807907,0.00006781075,0.9174569,0.06963392,0.0002891305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001079395,0.009121856,0.9804411,0.002037689,0.003705349,0.0008865187,0.0001663716,0.0000638838,0.002497854],"genre_scores_gemma":[0.9071631,0.02151699,0.0006289806,0.0002983028,0.0007735472,0.0001215396,0.0003151701,0.00003176046,0.06915064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9798121,"threshold_uncertainty_score":0.9999213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.12341697991583,"score_gpt":0.4437445261267874,"score_spread":0.3203275462109574,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}