Triple
T15863198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Котлин |
E384641
|
entity |
| Predicate | играетРоль |
P68592
|
FINISHED |
| Object | ключевая часть обороны подступов к Санкт-Петербургу |
—
|
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: ключевая часть обороны подступов к Санкт-Петербургу | Statement: [Котлин, играетРоль, ключевая часть обороны подступов к Санкт-Петербургу]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: играетРоль Context triple: [Котлин, играетРоль, ключевая часть обороны подступов к Санкт-Петербургу]
-
A.
playRoleIn
chosen
Indicates that an entity participates in or performs a specific function, character, or part within an event, context, or system.
-
B.
playsInRole
Indicates that an entity performs or appears in a specific role within a production, event, or context.
-
C.
playsAs
Indicates that one entity performs, portrays, or assumes the role, character, or persona of another entity.
-
D.
roleInGameplay
Indicates the specific function or responsibility an entity has within the context of gameplay or game mechanics.
-
E.
theaterRole
Indicates that an entity holds or performs a specific role or character in a theatrical production in relation to another entity (such as a play or performance).
- 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_69d86da422088190aac39e32e6c68429 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e174de2cd48190ab18e48c9f051a2a |
completed | April 16, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69e142b976c081908d3ba3e705419f3a |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:50 a.m.