Triple
T32838874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | People's Democratic Republic |
E839908
|
entity |
| Predicate | governmentFormIncludes |
P199483
|
FINISHED |
| Object | republican institutions |
—
|
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: republican institutions | Statement: [People's Democratic Republic, governmentFormIncludes, republican institutions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governmentFormIncludes Context triple: [People's Democratic Republic, governmentFormIncludes, republican institutions]
-
A.
governmentForms
chosen
Indicates the types or structures of governance that an entity establishes, adopts, or is organized under.
-
B.
governmentFormDefined
Indicates that the specific form or structure of governance for an entity has been formally specified or classified.
-
C.
governmentFormModeled
Indicates that one government form is modeled after, or structurally based on, another government form.
-
D.
governmentFormServed
Indicates that an entity has served in or held a position within a particular form or system of government.
-
E.
governmentFormAffected
Indicates that one entity has caused a change or influence on the form or structure of government of 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_69f3493ff0888190b51e974eae2a7834 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a007241df8081909dbad651fda82aa7 |
completed | May 10, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_6a0071e77ed081908cd618da8977d878 |
completed | May 10, 2026, 11:54 a.m. |
Created at: May 1, 2026, 1:16 a.m.