Triple
T17790804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bolshaya Neva |
E444154
|
entity |
| Predicate | flowsThroughPart |
P11198
|
FINISHED |
| Object | central Saint Petersburg |
—
|
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: central Saint Petersburg | Statement: [Bolshaya Neva, flowsThroughPart, central Saint Petersburg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flowsThroughPart Context triple: [Bolshaya Neva, flowsThroughPart, central Saint Petersburg]
-
A.
flowsThroughEntity
Indicates that a substance, medium, or influence moves along a path that passes through the referenced entity.
-
B.
flowsAt
Indicates that a fluid or substance moves through or along a specific location, point, or region.
-
C.
isPassedThroughBy
chosen
Indicates that something serves as a medium, route, or channel through which another thing moves, flows, or is transmitted.
-
D.
flowsOver
Indicates that one substance or medium moves across the surface or boundary of another, covering or passing above it.
-
E.
flowsFrom
Indicates that a substance, medium, or influence moves or originates from one entity or location and proceeds outward to another.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4879688908190a5428b1fa7525f62 |
completed | April 19, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:13 a.m.