Triple
T4958499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tula |
E111344
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Brest |
E41676
|
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: Brest | Statement: [Tula, hasTwinTown, Brest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brest Context triple: [Tula, hasTwinTown, Brest]
-
A.
Brest
Brest is a major port city in northwestern France that serves as one of the country’s principal naval and maritime centers.
-
B.
Brest (Belarus)
chosen
Brest is a city in southwestern Belarus near the Polish border, known as a major transport hub and for the historic Brest Fortress, a key World War II memorial.
-
C.
Pinsk
Pinsk is a historic city in southwestern Belarus, known for its location on the Pina River and its rich cultural and architectural heritage.
-
D.
Lvov
Lvov is a Russian noble family name most notably borne by Georgy Lvov, the first head of the Russian Provisional Government after the February Revolution of 1917.
-
E.
Vilna
Vilna is the historical name for Vilnius, the capital city of Lithuania and a major cultural and political center of the region.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71d834c0819087f3faafdc9b4228 |
completed | March 20, 2026, 4:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be81e4ccc4819090223633fdb04eee |
completed | March 21, 2026, 11:32 a.m. |
Created at: March 20, 2026, 1:32 p.m.