Triple
T8232568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miguel Primo de Rivera |
E192326
|
entity |
| Predicate | implementedGovernmentType |
P80989
|
FINISHED |
| Object | military dictatorship |
—
|
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 dictatorship | Statement: [Miguel Primo de Rivera, implementedGovernmentType, military dictatorship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: implementedGovernmentType Context triple: [Miguel Primo de Rivera, implementedGovernmentType, military dictatorship]
-
A.
basedInGovernmentType
Indicates that an entity operates within or is associated with a government of a specified governmental system or type.
-
B.
formedGovernmentWith
Indicates that two or more political entities joined together to establish or lead a government in partnership.
-
C.
hasCityGovernmentType
Indicates the specific form or structure of municipal governance that administers a city.
-
D.
formedGovernmentIn
Indicates that an entity established or took office as the governing authority of a political unit in a specified place or jurisdiction.
-
E.
typeOfGovernmentAfter
Indicates the form of government that exists or is established in a place following a specified event or time period.
- 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_69ca82db5b90819085d1ad7c2e27bfcc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb782658fc8190885dc267355ff245 |
completed | March 31, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69cb36b1dea0819091418072501e79c1 |
completed | March 31, 2026, 2:51 a.m. |
| PDg | Predicate description generation | batch_69cb3d6c34708190a987d68529cbb0b3 |
completed | March 31, 2026, 3:20 a.m. |
Created at: March 30, 2026, 5:46 p.m.