Triple
T19866758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Donbas (2022) |
E477410
|
entity |
| Predicate | frontlineCity |
P3207
|
FINISHED |
| Object | Rubizhne |
—
|
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: Rubizhne | Statement: [Battle of Donbas (2022), frontlineCity, Rubizhne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rubizhne Context triple: [Battle of Donbas (2022), frontlineCity, Rubizhne]
-
A.
Rubizhne
chosen
Rubizhne is an industrial city in eastern Ukraine known for its chemical and manufacturing industries and its location within the conflict-affected Donbas region.
-
B.
Darnytsia
Darnytsia is a station on the Kyiv Metro system in Ukraine, serving the Sviatoshynsko–Brovarska line on the city's left bank.
-
C.
Vasylkivska
Vasylkivska is a station on the Kyiv Metro system in Ukraine.
-
D.
Yaremche
Yaremche is a picturesque resort town in western Ukraine’s Carpathian Mountains, known for its scenic landscapes, waterfalls, and hiking opportunities.
-
E.
Pervomaiskyi
Pervomaiskyi is a small industrial city in eastern Ukraine known for its chemical industry and location within Kharkiv Oblast.
- 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6589f9654819080597a4f7c52d64c |
completed | April 20, 2026, 4:47 p.m. |
Created at: April 10, 2026, 1:51 p.m.