Triple
T24403962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurskiy Zaliv |
E615255
|
entity |
| Predicate | belongsToMarineRegion |
P139259
|
FINISHED |
| Object | Southeastern Baltic Sea |
—
|
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: Southeastern Baltic Sea | Statement: [Kurskiy Zaliv, belongsToMarineRegion, Southeastern Baltic Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToMarineRegion Context triple: [Kurskiy Zaliv, belongsToMarineRegion, Southeastern Baltic Sea]
-
A.
belongsToSea
Indicates that something is a part of, contained within, or naturally associated with a particular sea.
-
B.
belongsToOceanicRegion
Indicates that one entity is geographically or administratively situated within, or associated with, a specified oceanic region.
-
C.
hasMarineEcoregion
Indicates that an entity is associated with, or located within, a specific marine ecoregion.
-
D.
nauticalRegion
chosen
Indicates that one entity is a maritime or nautical area within which the other entity is located, operates, or is relevant.
-
E.
hasRegion
Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
- 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_69e2d7e780bc81908049c779e697a7f6 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f294dcf7f4819094d2a3be163a5822 |
completed | April 29, 2026, 11:31 p.m. |
| PD | Predicate disambiguation | batch_69f287c4a2b48190b80fb7a3c0e9b018 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:05 a.m.