Triple
T19518194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kemsky Bridge |
E488332
|
entity |
| Predicate | crosses |
P416
|
FINISHED |
| Object | Malaya Nevka |
E60916
|
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: Malaya Nevka | Statement: [Kemsky Bridge, crosses, Malaya Nevka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Malaya Nevka Context triple: [Kemsky Bridge, crosses, Malaya Nevka]
-
A.
Malaya Nevka
chosen
Malaya Nevka is a distributary channel of the Neva River in Saint Petersburg, Russia, forming part of the city’s intricate river and canal network.
-
B.
Navalnaya
Navalnaya is the surname of Yulia Navalnaya, a Russian public figure and the widow of opposition leader Alexei Navalny.
-
C.
Rizhskaya
Rizhskaya is a Moscow Metro station on the Big Circle Line serving the Rizhsky railway terminal area.
-
D.
Nakhimovskaya
Nakhimovskaya is an alternative form of the Russian place name Nakhimovskoye, typically reflecting feminine grammatical gender in Russian toponymy.
-
E.
Komsomolskaya
Komsomolskaya is one of Moscow Metro’s most famous and ornate stations, renowned for its grand Baroque-style decor and elaborate mosaics.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6359da24c81909a0fd165a0fc0e33 |
completed | April 20, 2026, 2:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a074727002c8190aa3783c66242a4e4 |
completed | May 15, 2026, 4:17 p.m. |
Created at: April 10, 2026, 1:40 p.m.