Triple
T158916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Army Secretariat |
E3236
|
entity |
| Predicate | typeOfControl |
P6850
|
FINISHED |
| Object | civilian leadership over military service |
—
|
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: civilian leadership over military service | Statement: [Army Secretariat, typeOfControl, civilian leadership over military service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfControl Context triple: [Army Secretariat, typeOfControl, civilian leadership over military service]
-
A.
typeOfOperation
Indicates the specific kind or category of operation being performed or referenced in a given context.
-
B.
typeOfContract
Indicates the specific kind or category of contractual agreement that applies between the related entities.
-
C.
fieldType
Indicates the classification or category that defines the nature or kind of a given field within a structure or context.
-
D.
typeOfSupport
Indicates the kind or category of assistance, help, or backing provided in a given context.
-
E.
typeOf
Indicates that one entity is a specific kind, class, or category instance of another more general entity.
- F. None of above. chosen
Provenance (4 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a2583169a0819081b658882e5bc452 |
completed | Feb. 28, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69a25660c2a48190b4174d5e6da3cb9d |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2580b00988190868ee24c0289cf70 |
completed | Feb. 28, 2026, 2:50 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.