Triple

T27573403
Position Surface form Disambiguated ID Type / Status
Subject Atta Muhammad Nur E696092 entity
Predicate securityBase P164824 FINISHED
Object Balkh provincial police and militias
The Balkh provincial police and militias are the regional security forces in Afghanistan’s Balkh Province that were effectively controlled and influenced by powerful local leader Atta Muhammad Nur.
E1778244 NE FINISHED

How this triple was built (3 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: Balkh provincial police and militias | Statement: [Atta Muhammad Nur, securityBase, Balkh provincial police and militias]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Balkh provincial police and militias
Triple: [Atta Muhammad Nur, securityBase, Balkh provincial police and militias]
Generated description
The Balkh provincial police and militias are the regional security forces in Afghanistan’s Balkh Province that were effectively controlled and influenced by powerful local leader Atta Muhammad Nur.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: securityBase
Context triple: [Atta Muhammad Nur, securityBase, Balkh provincial police and militias]
  • A. securityBasisFor
    Indicates that one entity serves as the justification, foundation, or underlying reason for the security of another entity.
  • B. securityAspect
    Indicates a relationship where something pertains to, represents, or characterizes a particular aspect or dimension of security.
  • C. securityDependence chosen
    Indicates a relationship where one entity relies on another to ensure its safety, protection, or defense from threats.
  • D. securityAccess
    Indicates that one entity has permission, authorization, or the ability to access or interact with another entity in a security-controlled context.
  • E. securityPillar
    Indicates that one entity functions as a foundational security pillar or core security domain in relation to another entity.
  • F. None of above.

Provenance (6 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_69ef53891af88190a193c5e2a1dac9b1 completed April 27, 2026, 12:16 p.m.
NER Named-entity recognition batch_69f67c9fe7b48190b79b4041357edb49 completed May 2, 2026, 10:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12c5d4b98881908b3a709f933ba943 completed May 24, 2026, 9:33 a.m.
NEDg Description generation batch_6a12c73b99948190b0b9b9fc080317bb completed May 24, 2026, 9:39 a.m.
NED2 Entity disambiguation (via description) batch_6a12c7b518a88190af3af56ac1ba03dd completed May 24, 2026, 9:41 a.m.
PD Predicate disambiguation batch_69f678cc272081909e5c70f1bc7407f0 completed May 2, 2026, 10:21 p.m.
Created at: April 27, 2026, 1:44 p.m.