Triple
T36345507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дворцовая набережная |
E895052
|
entity |
| Predicate | пролегаетДо |
P151412
|
FINISHED |
| Object | Троицкий мост |
—
|
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: Троицкий мост | Statement: [Дворцовая набережная, пролегаетДо, Троицкий мост]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: пролегаетДо Context triple: [Дворцовая набережная, пролегаетДо, Троицкий мост]
-
A.
routeOf
Indicates that one entity is the path, course, or trajectory taken or followed by another entity (such as a vehicle, shipment, or signal).
-
B.
ultimatePathTo
Indicates that one entity represents the final, most fundamental, or decisive route, method, or means by which another entity is reached or achieved.
-
C.
hasLongerReachThan
Indicates that one entity can extend, influence, or physically reach farther than another entity.
-
D.
isStartingPointOf
Indicates that something serves as the initial point or origin from which another thing, process, or path begins.
-
E.
routeAlong
chosen
Indicates that one entity follows, runs parallel to, or is situated along the course or path defined by another 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bcccd7988190aa5c931ff347d33c |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:09 p.m.