Triple

T3602124
Position Surface form Disambiguated ID Type / Status
Subject Directorate for Analysis E76279 entity
Predicate usesIntelligenceSources P26860 FINISHED
Object human intelligence LITERAL FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: human intelligence | Statement: [Directorate for Analysis, usesIntelligenceSources, human intelligence]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usesIntelligenceSources
Context triple: [Directorate for Analysis, usesIntelligenceSources, human intelligence]
  • A. usesInformationSources chosen
    Indicates that an entity relies on or consults specified information sources to perform actions, make decisions, or obtain knowledge.
  • B. providesIntelligenceTo
    Indicates that one entity supplies information, analysis, or insight that enhances the knowledge or decision-making capability of another entity.
  • C. intelligenceSource
    Indicates that one entity serves as the origin or provider of intelligence information for another entity.
  • D. intelligenceAgencyInvolved
    Indicates that an intelligence agency participates in, influences, or is otherwise involved in the referenced event, operation, or relationship.
  • E. usesInvestigativeMethods
    Indicates that an entity employs investigative techniques or procedures to gather information, analyze evidence, or uncover facts.
  • F. None of above.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ad85d93dcc819094fba90cf70f4996 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc1dd264c819098796f5f50f251be completed March 8, 2026, 6:37 p.m.
PD Predicate disambiguation batch_69adb83b66708190bb9d2f23d6fd308e completed March 8, 2026, 5:56 p.m.
Created at: March 8, 2026, 3:22 p.m.