Triple
T34766286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief Judge Griffin |
E1002223
|
entity |
| Predicate | governmentFormInSetting |
P40139
|
FINISHED |
| Object | judicial 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: judicial dictatorship | Statement: [Chief Judge Griffin, governmentFormInSetting, judicial dictatorship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governmentFormInSetting Context triple: [Chief Judge Griffin, governmentFormInSetting, judicial dictatorship]
-
A.
governmentFormModeled
Indicates that one government form is modeled after, or structurally based on, another government form.
-
B.
governmentFormDefined
chosen
Indicates that the specific form or structure of governance for an entity has been formally specified or classified.
-
C.
governmentForms
Indicates the types or structures of governance that an entity establishes, adopts, or is organized under.
-
D.
governmentFormUnder
Indicates that one governmental form or system operates under the authority, framework, or jurisdiction of another governmental form.
-
E.
governmentFormAdvocated
Indicates the specific form of government that an entity promotes, supports, or argues should be adopted.
- 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_69f76db20dac8190b1e8d0ca4dc1d59f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a016777257081908841c5522dfa76e6 |
completed | May 11, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_6a0164e49bec8190af3c8626be9677a9 |
completed | May 11, 2026, 5:11 a.m. |
Created at: May 3, 2026, 3:59 p.m.