Triple
T17966386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bryansk Oblast |
E449218
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Dyatkovo |
—
|
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: Dyatkovo | Statement: [Bryansk Oblast, containsTown, Dyatkovo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dyatkovo Context triple: [Bryansk Oblast, containsTown, Dyatkovo]
-
A.
Dyatkovo
chosen
Dyatkovo is a town in western Russia known historically for its glassmaking industry and as an administrative center within Bryansk Oblast.
-
B.
Ustyuzhna
Ustyuzhna is a historic town in Vologda Oblast, Russia, known for its traditional architecture and role as a local administrative and cultural center.
-
C.
Kastornoye
Kastornoye is a locality in Russia historically notable as the namesake and focal area of the Voronezh–Kastornoye military offensive during World War II.
-
D.
Kuvshinovo
Kuvshinovo is a small town in Tver Oblast, Russia, known primarily as a local industrial and administrative center.
-
E.
Dubrovitsy
Dubrovitsy is a historic rural locality in Moscow Oblast, Russia, known for its ornate baroque Church of the Theotokos of the Sign and its scenic setting near the city of Podolsk.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1380960819089a3c0dd7cd57e5e |
completed | April 19, 2026, 10:40 a.m. |
Created at: April 10, 2026, 10:22 a.m.