LLM + Neutrosophic fsQCA: Inter-Narrative Causal Consistency and Paraconsistent Detection in Media Accounts of Urban Violence in Guayaquil

Urban violence in Guayaquil, Ecuador has reached crisis levels, yet causal explanations remain fragmented across local and international media. This paper introduces N-fsQCA, a Neutrosophic extension of fuzzy-set Qualitative Comparative Analysis (fsQCA), and combines it with Large Language Models (LLMs) to extract and compare causal narratives from a bilingual corpus of 31 sources (16 local Spanish-language, 15 international English-language). Four LLMs (Google Gemini-2.0-Flash-Lite, Meta LLaMA-3.1-8B, Microsoft Phi-4, Qwen-3-8B) assign fuzzy scores [0,1] to eight causal conditions; indeterminacy (I) is operationalized as inter-LLM variance (Var/0.25), capturing epistemic disagreement as structural information. Results show: (i) the configuration territorial_war * prison_linkages achieves the highest consistency (T=0.908, I=0.092); (ii) international media emphasizes drug routes (gap=+0.330) and prison linkages (gap=+0.309) at roughly double the rate of local media; (iii) five structural drivers are systematically silenced in the press, with weapons trafficking showing the largest gap (-0.444) against a structural baseline derived from a validated perception survey (n=179) and grey literature. The pipeline is open-source (MIT License).