Triple

T37157610
Position Surface form Disambiguated ID Type / Status
Subject Lord Auckland E920552 entity
Predicate resultOfAfghanPolicy P168947 FINISHED
Object military disaster for the British in Afghanistan 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: military disaster for the British in Afghanistan | Statement: [Lord Auckland, resultOfAfghanPolicy, military disaster for the British in Afghanistan]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: resultOfAfghanPolicy
Context triple: [Lord Auckland, resultOfAfghanPolicy, military disaster for the British in Afghanistan]
  • A. strategicObjectiveAfghan
    Indicates that an entity has a strategic objective specifically related to Afghanistan or Afghan affairs.
  • B. resultForPolicy
    Indicates that a particular outcome, evaluation, or result is associated with and produced under a specific policy.
  • C. importanceInAfghanistan
    Indicates the degree to which something holds significance, influence, or priority specifically within the context of Afghanistan.
  • D. consequenceOfPolicies chosen
    Indicates the outcomes or effects that result from the implementation or existence of specific policies.
  • E. statusInAfghanistan
    Indicates the condition, role, or legal standing an entity holds within the context of Afghanistan.
  • 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_69f76ea0429081908c711b55599eac3c completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fdbc5ef46c8190bbcfb9798f4615b7 completed May 8, 2026, 10:35 a.m.
PD Predicate disambiguation batch_69fdbb270338819082ce3f73903e884f completed May 8, 2026, 10:29 a.m.
Created at: May 3, 2026, 4:15 p.m.