Triple
T16867201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navahrudak |
E410071
|
entity |
| Predicate | hasNameInRussian |
P20560
|
FINISHED |
| Object | Новогрудок |
E780998
|
NE 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: Новогрудок | Statement: [Navahrudak, hasNameInRussian, Новогрудок]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Новогрудок Context triple: [Navahrudak, hasNameInRussian, Новогрудок]
-
A.
Novogrudok
chosen
Novogrudok is a historic town in western Belarus known as one of the early political centers of the Grand Duchy of Lithuania.
-
B.
Horodnia
Horodnia is a small town in northern Ukraine known for its historical roots and location within the Chernihiv region.
-
C.
Vishnevo
Vishnevo is a village historically located in the former Second Polish Republic, known today as Wiszniew and situated in present-day Belarus.
-
D.
Velykyi Zhytyn
Velykyi Zhytyn is a village in western Ukraine notable as the birthplace of the country’s first president, Leonid Kravchuk.
-
E.
Volochysk
Volochysk is a town in western Ukraine known as a local administrative and transportation center near the border with Ternopil Oblast.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b50983148190a116f7e7017ccb1c |
completed | April 18, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2aba8c481908f5ff1ddc4b255cb |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:24 a.m.