Triple
T8029623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baltiysk |
E186943
|
entity |
| Predicate | positionInRussia |
P75615
|
FINISHED |
| Object | westernmost town of Russia |
—
|
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: westernmost town of Russia | Statement: [Baltiysk, positionInRussia, westernmost town of Russia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInRussia Context triple: [Baltiysk, positionInRussia, westernmost town of Russia]
-
A.
positionOnRussia
Indicates the stance, opinion, or policy that one entity holds regarding Russia.
-
B.
isLocatedRelativeToMoscow
Indicates a spatial relationship specifying where an entity is situated in relation to the city of Moscow.
-
C.
statusInRussia
Indicates the legal, social, or operational condition or standing that something or someone has specifically within the context of Russia.
-
D.
distanceFromMoscow_km
Indicates the physical distance, measured in kilometers, between a given entity’s location and Moscow.
-
E.
positionOnTerritory
chosen
Indicates that one entity occupies or is located at a specific position within the spatial extent of another entity’s territory.
- 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_69ca82ad4e2c8190a693e3c9e30fe66f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ecf0f2c819091899211003c461e |
completed | March 31, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69cb049688208190b32088bd2c5930bc |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:21 p.m.