Triple
T13013749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angara River |
E322487
|
entity |
| Predicate | hasMajorCityOnBank |
P7935
|
FINISHED |
| Object | Bratsk |
E466444
|
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: Bratsk | Statement: [Angara River, hasMajorCityOnBank, Bratsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bratsk Context triple: [Angara River, hasMajorCityOnBank, Bratsk]
-
A.
Bratsk
chosen
Bratsk is a major industrial city in Siberia, Russia, best known for its large hydroelectric power station and aluminum production facilities.
-
B.
Lesosibirsk
Lesosibirsk is a town in central Siberia, Russia, known historically as a major timber-processing and river port center on the Yenisei River.
-
C.
Verkhnyaya Troitsa
Verkhnyaya Troitsa is a rural locality in Russia best known as the birthplace of Soviet statesman and longtime nominal head of state Mikhail Kalinin.
-
D.
Ust-Sheksna
Ust-Sheksna is the former historical name of the Russian town now known as Rybinsk, an important port city on the Volga River.
-
E.
Ust-Izhora
Ust-Izhora is a settlement in the Leningrad Oblast of Russia located at the confluence of the Izhora and Neva rivers, historically notable as a strategic and trading point.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecbb8f4819094d55eb07cb5ad97 |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f0dddc88190918d3a071b75a556 |
completed | May 3, 2026, 10:10 a.m. |
Created at: April 9, 2026, 8:50 p.m.