Triple
T16308398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Володарский мост |
E395979
|
entity |
| Predicate | служит для |
P98
|
FINISHED |
| Object | соединение районов Санкт-Петербурга |
—
|
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: соединение районов Санкт-Петербурга | Statement: [Володарский мост, служит для, соединение районов Санкт-Петербурга]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: служит для Context triple: [Володарский мост, служит для, соединение районов Санкт-Петербурга]
-
A.
usedForService
Indicates that one entity is employed, utilized, or designated to perform, support, or provide a particular service for another entity.
-
B.
serviceFor
Indicates that one entity provides a service or performs functions on behalf of another entity.
-
C.
usedFor
chosen
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
D.
servesUse
Indicates that one entity is used by or functions to serve the purpose or needs of another entity.
-
E.
providesServiceTowards
Indicates that one entity delivers or performs a service directed to or for the benefit of 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288d776808190a7c9918477f07216 |
completed | April 17, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.