Triple
T34962691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Могилёв-Подольский |
E1008301
|
entity |
| Predicate | находитсяНаБерегу |
P84004
|
FINISHED |
| Object | Днестровское водохранилище |
—
|
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: Днестровское водохранилище | Statement: [Могилёв-Подольский, находитсяНаБерегу, Днестровское водохранилище]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: находитсяНаБерегу Context triple: [Могилёв-Подольский, находитсяНаБерегу, Днестровское водохранилище]
-
A.
locatedOnCoastAt
chosen
Indicates that one entity is situated on the coastline at the specific location represented by another entity.
-
B.
находитсяК
Indicates that one entity is located at, in, or near another entity.
-
C.
locatedOnEasternShoreOf
Indicates that one entity is situated on the eastern shore or bank of another geographic feature, such as a body of water or landform.
-
D.
connectsToCoastAt
Indicates that one entity has a direct physical or geographical connection or access to a coastline at the location of another entity.
-
E.
locatedAtSea
Indicates that something exists or is situated in or on the sea.
- 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_69f76dc69564819099e9e78aed6ff0a6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78710282c81909146dc0be91e983f |
completed | May 3, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f784162134819098413482ef52042f |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4 p.m.