Triple
T90548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secretary of State for War |
E1818
|
entity |
| Predicate | oversaw |
P760
|
FINISHED |
| Object | War Office civil administration |
—
|
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: War Office civil administration | Statement: [Secretary of State for War, oversaw, War Office civil administration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oversaw Context triple: [Secretary of State for War, oversaw, War Office civil administration]
-
A.
oversawEvent
Indicates that an entity had supervisory or managerial responsibility for the planning, execution, or overall conduct of an event.
-
B.
overlooks
Indicates that one entity has a view toward or looks out over another entity, typically from a higher or adjacent position.
-
C.
governs
chosen
Indicates that one entity exercises authoritative control, direction, or rule over another entity or domain.
-
D.
governedAs
Indicates that one entity exercises authoritative control, direction, or rule over another according to some system of governance or leadership.
-
E.
commandedBy
Indicates that one entity holds authoritative control or issues orders over another entity.
- 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a24feef1b08190bb9525f71cce053e |
completed | Feb. 28, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69a24eb82d408190b0f9c786152e8e4c |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.