Triple

T24818143
Position Surface form Disambiguated ID Type / Status
Subject United States–Vietnam relations E620980 entity
Predicate warLegacyIssue P149202 FINISHED
Object Agent Orange remediation 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: Agent Orange remediation | Statement: [United States–Vietnam relations, warLegacyIssue, Agent Orange remediation]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: warLegacyIssue
Context triple: [United States–Vietnam relations, warLegacyIssue, Agent Orange remediation]
  • A. warLegacy
    Indicates that a past war has left lasting impacts or consequences on an entity, such as social, political, economic, or cultural effects that persist over time.
  • B. militaryIssue
    Indicates that one entity formally provides or distributes military-related items, orders, or directives to another entity.
  • C. warCustom
    Indicates a relationship in which one party engages in or applies a particular war-related practice, norm, or customary way of conducting warfare toward or involving another.
  • D. hasPostWarIssues chosen
    Indicates that an entity experiences problems, challenges, or complications that arise in the period following a war or major conflict.
  • E. historicalIssue
    Indicates that one entity is a past or previously existing edition, version, or instance of another entity, typically within a chronological sequence.
  • 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_69e2fabfd4648190bd0e5c7f4dbb6cab completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f44a417a58819081777e18dda149fd completed May 1, 2026, 6:37 a.m.
PD Predicate disambiguation batch_69f442b8479c8190a7c8e416ac9e28a0 completed May 1, 2026, 6:05 a.m.
Created at: April 18, 2026, 5:03 a.m.