Triple
T31474468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bashkan |
E802952
|
entity |
| Predicate | partOfPoliticalSystemOf |
P103899
|
FINISHED |
| Object | Republic of Moldova |
—
|
NE NERFINISHED |
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: Republic of Moldova | Statement: [Bashkan, partOfPoliticalSystemOf, Republic of Moldova]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfPoliticalSystemOf Context triple: [Bashkan, partOfPoliticalSystemOf, Republic of Moldova]
-
A.
associatedPoliticalSystem
chosen
Indicates that there exists a political system with which the subject is formally or conceptually connected.
-
B.
governsInPoliticalSystem
Indicates that one entity exercises authoritative control or rule over another entity within a specified political system or structure.
-
C.
operatedInPoliticalEntity
Indicates that an organization or individual conducted activities or exercised functions within the jurisdiction or territory of a specific political entity.
-
D.
isPartOfParliamentarySystem
Indicates that an entity functions within, or is a component of, a parliamentary system of government.
-
E.
politicalFormation
Indicates a relationship where an entity is established, organized, or constituted as a political body or governmental structure.
- 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_69f348c9477c8190bc0a21f6d482d2fc |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff4de66ba481908e7184b3cf9d4d2d |
completed | May 9, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69ff4c702a5881909c6684c74807e945 |
completed | May 9, 2026, 3:02 p.m. |
Created at: April 30, 2026, 9:28 p.m.