Fact-checking
AuraScore 81/100

Humanitarian Crisis Situational Report Fact-Verification Matrix

Cross-examine unverified field dispatches, casualty figures, and aid delivery metrics during public sector humanitarian crises.

Use this template during humanitarian emergencies or public sector disaster response when disparate, high-stakes situational reports must be vetted against satellite baselines, institutional telemetry, and field data before public release or resource deployment.

Template

Role: Lead Humanitarian Information Verification Officer with the UN/OCHA or civil protection crisis taskforce.

Context

  • Raw field dispatch data: {{field_sitrep_text}}
  • Contested figures or events: {{disputed_casualty_claims}}
  • Submitting NGO/field entities: {{reporting_humanitarian_actors}}
  • Geospatial and remote sensing data: {{independent_satellite_baselines}}
  • Operational theater boundaries: {{conflict_zone_parameters}}
  • Standard verification rubric: {{confidence_scoring_rubric}}

Task

Cross-examine all field claims in {{field_sitrep_text}} against {{independent_satellite_baselines}} and official operational parameters, producing a Crisis Situational Fact-Verification Matrix to prevent misinformation and misdirected humanitarian resource allocation.

Method

  1. Disaggregate {{field_sitrep_text}} into testable incident units: casualty counts, population displacements, infrastructure destruction, and supply bottlenecks.
  2. Isolate high-risk claims defined in {{disputed_casualty_claims}} for prioritized multi-source corroboration.
  3. Correlate geographic and temporal coordinates against {{conflict_zone_parameters}} to confirm jurisdiction and event plausibility.
  4. Cross-reference physical damage and movement reports against {{independent_satellite_baselines}} and geospatial telemetry.
  5. Calibrate the credibility weight of {{reporting_humanitarian_actors}} based on historical reporting reliability and on-the-ground access.
  6. Run cross-source reconciliation between competing operational field transmissions to identify narrative divergences.
  7. Score information confidence for each discrete incident according to {{confidence_scoring_rubric}} (Confirmed, Probable, Possible, Uncorroborated, Disproven).
  8. Determine whether operational deployment or public release is approved for each metric.

Constraints

  • MUST flag any metric involving {{disputed_casualty_claims}} as Uncorroborated unless backed by at least two independent telemetry streams.
  • MUST NOT extrapolate population counts beyond confirmed baseline parameters in {{conflict_zone_parameters}}.
  • Every incident entry must include an explicit verification timeline tag.
  • Humanitarian 'do no harm' information security principles must be observed.

Output format

Structure the deliverable into:

  1. Situation Verification Overview (Audit Scope, Uncorroborated Claim Ratio, Critical Alerts).
  2. Humanitarian Fact-Verification Matrix formatted as a markdown table with columns: [Incident ID | Claim Description | Reporting Actor | Independent Telemetry Match | Reconciliation Finding | Verification Tier | Actionable Status (Release/Hold/Reject)].
  3. Intelligence Gaps and Satellite Tasking Priorities (bulleted list of unverified locations requiring remote sensing).

Self-review

  • Confirm that no uncorroborated casualty claim is marked with an actionable status of 'Release'.
  • Check that geospatial claims physically align with {{independent_satellite_baselines}}.
  • Validate that all scoring aligns strictly with {{confidence_scoring_rubric}}.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-fact-checking
public-sector-nonprofit
humanitarian-aid
crisis-response
fact-checking