Triple
T28284605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yaroslavl Embankment |
E713245
|
entity |
| Predicate | hasToponymInRussian |
P24399
|
FINISHED |
| Object | Ярославская набережная |
—
|
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: Ярославская набережная | Statement: [Yaroslavl Embankment, hasToponymInRussian, Ярославская набережная]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasToponymInRussian Context triple: [Yaroslavl Embankment, hasToponymInRussian, Ярославская набережная]
-
A.
hasLanguageOfToponym
chosen
Indicates that a place name (toponym) is expressed in or associated with a particular language.
-
B.
hasToponymicForm
Indicates that one entity is a toponymic (place-name-based) form or variant derived from another entity.
-
C.
includesToponym
Indicates that one entity contains or references a place name (toponym) associated with another entity.
-
D.
isToponymIn
Indicates that a place name (toponym) is located within or refers to a specific geographic area or region.
-
E.
hasOriginToponym
Indicates that something originates from, or is derived from, the place denoted by a specific toponym (geographical name).
- 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_69efb52371d88190a1381c4e58a3b731 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 27, 2026, 11:25 p.m.