Triple

T6724991
Position Surface form Disambiguated ID Type / Status
Subject Pierre de Villiers E153493 entity
Predicate postMilitaryActivity P40607 FINISHED
Object public speaking on leadership and defence 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: public speaking on leadership and defence | Statement: [Pierre de Villiers, postMilitaryActivity, public speaking on leadership and defence]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: postMilitaryActivity
Context triple: [Pierre de Villiers, postMilitaryActivity, public speaking on leadership and defence]
  • A. militaryActivity
    Indicates that an entity is engaged in, associated with, or affected by actions, operations, or preparations conducted by armed forces.
  • B. postMilitaryCareer chosen
    Indicates that one entity’s career or occupation occurs after the completion of their military service.
  • C. postMilitaryUse
    Indicates that an entity is used or repurposed after its original military function or service has ended.
  • D. closedAsActiveArmyPost
    Indicates that a location or facility ceased operations specifically in its role as an active Army post.
  • E. militaryEventMentionedIn
    Indicates that a specific military event is referenced or discussed within a particular document, text, or source.
  • 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_69c6880afb988190ad88011b48ecfcba completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d354177481908ab3cf5437c095e2 completed March 27, 2026, 6:58 p.m.
PD Predicate disambiguation batch_69c6d08e8a2c8190ae4e8d8c039be7ce completed March 27, 2026, 6:46 p.m.
Created at: March 27, 2026, 2:08 p.m.