Triple
T33781929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Petersburg–Sortavala route |
E865678
|
entity |
| Predicate | hasIntermediateLocality |
P45140
|
FINISHED |
| Object | Priozersk |
—
|
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: Priozersk | Statement: [Saint Petersburg–Sortavala route, hasIntermediateLocality, Priozersk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIntermediateLocality Context triple: [Saint Petersburg–Sortavala route, hasIntermediateLocality, Priozersk]
-
A.
containsLocality
chosen
Indicates that one place or area geographically includes or encompasses another locality within its boundaries.
-
B.
hasTypeLocality
Indicates the specific geographic location where an entity (typically a species or specimen) was originally found and formally described.
-
C.
hasImportantLocality
Indicates that something possesses or is associated with a locality (place or region) that is considered significant or particularly relevant in the given context.
-
D.
hasIntermediate
Indicates that there exists one or more entities that serve as a middle or transitional step between two related entities or stages.
-
E.
hasIntermediateArea
Indicates that there exists an area or region that lies between or connects two other areas in the relationship.
- 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_69f3498ecc2c8190bcd85e3f11dc215e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a0004582bb08190b8d0b88251e8d333 |
completed | May 10, 2026, 4:06 a.m. |
| PD | Predicate disambiguation | batch_6a0003e3e5588190933beea5fb28f150 |
completed | May 10, 2026, 4:04 a.m. |
Created at: May 1, 2026, 1:45 a.m.