Triple

T11150336
Position Surface form Disambiguated ID Type / Status
Subject Afghanistan–United States relations E263766 entity
Predicate U.S.aidFocusSector P72661 FINISHED
Object infrastructure 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: infrastructure | Statement: [Afghanistan–United States relations, U.S.aidFocusSector, infrastructure]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: U.S.aidFocusSector
Context triple: [Afghanistan–United States relations, U.S.aidFocusSector, infrastructure]
  • A. providedMilitaryAidTo
    Indicates that one entity has supplied military assistance, such as weapons, training, funding, or logistical support, to another entity.
  • B. internationalAid
    Indicates the provision of assistance or resources from one country or international entity to another, typically to support development, relief, or crisis response.
  • C. receivesMilitaryAidFrom
    Indicates that one entity obtains military assistance, such as equipment, training, or funding, from another entity.
  • D. budgetarySector
    Indicates that an entity belongs to, is funded through, or is managed within a particular government or organizational budgetary sector.
  • E. fundingFocus chosen
    Indicates that one entity’s funding is directed toward or prioritized for a particular target, theme, or area of activity.
  • 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_69d6aa9ccddc8190868998c8b7beb060 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8719e74819095413abc6c79296c completed April 9, 2026, 5:57 p.m.
PD Predicate disambiguation batch_69d75ce71944819089eee9b5c9283cbd completed April 9, 2026, 8:01 a.m.
Created at: April 8, 2026, 9:28 p.m.