Triple
T16308394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Володарский мост |
E395979
|
entity |
| Predicate | категория объекта |
P87
|
FINISHED |
| Object | градостроительный объект |
—
|
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: градостроительный объект | Statement: [Володарский мост, категория объекта, градостроительный объект]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: категория объекта Context triple: [Володарский мост, категория объекта, градостроительный объект]
-
A.
categoryExample
Indicates that something is an example or instance illustrating a particular category.
-
B.
classificationAccordingTo
Indicates that an entity is assigned a particular class, type, or category as defined or determined by a specified source, standard, or authority.
-
C.
category
chosen
Indicates that one entity is classified as a member or type within the grouping or class defined by another entity.
-
D.
functionCategory
Indicates that one function is classified as belonging to a particular functional category or type.
-
E.
canonicalCategory
Indicates that an entity is assigned to its primary or standard category within a classification system.
- 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.