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.