Triple
T9025044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Заячий остров |
E216025
|
entity |
| Predicate | расположенНапротив |
P3232
|
FINISHED |
| Object | Дворцовая набережная |
—
|
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: Дворцовая набережная | Statement: [Заячий остров, расположенНапротив, Дворцовая набережная]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: расположенНапротив Context triple: [Заячий остров, расположенНапротив, Дворцовая набережная]
-
A.
positionedAgainst
Indicates that one entity is placed so that it directly faces or is set opposite to another entity, often in close or contacting alignment.
-
B.
opposingLocation
chosen
Indicates that two entities are located directly opposite each other, typically across a defined reference such as a street, corridor, or boundary.
-
C.
positionOpposed
Indicates that two entities hold positions or stances that are in direct conflict or opposition to each other.
-
D.
opposite
Indicates that one entity is positioned or oriented directly across from, or in a contrary or reverse relation to, another entity.
-
E.
locatedBehind
Indicates that one entity is positioned at the rear of or on the far side of another entity along a given viewing or reference direction.
- 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_69ca83a5fa88819088144801b4dd7245 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a7b902c81909fcbdc433a1acf7a |
completed | April 1, 2026, 12:44 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee132f08190940749c7c522e4c1 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:07 p.m.