Triple
T20064329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slavyanka Mountain |
E499566
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Slavianka |
—
|
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: Slavianka | Statement: [Slavyanka Mountain, alternativeName, Slavianka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Slavianka Context triple: [Slavyanka Mountain, alternativeName, Slavianka]
-
A.
Славянка
Славянка — это река в Ленинградской области и Санкт-Петербурге, являющаяся левым притоком Невы и известная своим живописным течением через Павловский парк.
-
B.
Orlová
Orlová is a town in the Moravian-Silesian Region of the Czech Republic, historically associated with coal mining and heavy industry.
-
C.
Slavyanka
chosen
Slavyanka is a port town in Russia’s Primorsky Krai, known as a coastal settlement on the Sea of Japan near Vladivostok.
-
D.
Krasava
Krasava is a character from Czech legend and literature associated with the tale of Princess Libuše and the early history of Bohemia.
-
E.
Prusakova
Prusakova is the maiden surname of Marina Oswald, the Russian-born widow of Lee Harvey Oswald.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e663787190819096b2b78b38c1bf12 |
completed | April 20, 2026, 5:33 p.m. |
Created at: April 11, 2026, 3:39 p.m.