Triple
T24362592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yaroslav Kuzminov |
E614103
|
entity |
| Predicate | typeOfEconomist |
P43012
|
FINISHED |
| Object | Russian economist |
—
|
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: Russian economist | Statement: [Yaroslav Kuzminov, typeOfEconomist, Russian economist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfEconomist Context triple: [Yaroslav Kuzminov, typeOfEconomist, Russian economist]
-
A.
typeOfAnalyst
Indicates that one entity serves as a specific kind or category of analyst in relation to another entity.
-
B.
typeOfScientist
chosen
Indicates that one entity is a scientist and the other specifies the kind or specialization of that scientist.
-
C.
keyEconomicReformer
Indicates that an entity plays a leading or pivotal role in initiating, driving, or shaping significant economic reforms.
-
D.
hasEconomicIdea
Indicates that an entity possesses, proposes, or is associated with a particular economic concept, theory, or viewpoint.
-
E.
economicSchool
Indicates that one entity is associated with, follows, or is classified under a particular school or tradition of economic thought represented by the other 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_69e2d7dfe7f08190b7a1f3a36483ab05 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29385d0d48190b04154fcc3efe49a |
completed | April 29, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2 a.m.