Triple
T5638443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taras Bulba |
E124205
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Taras Bulba (character) |
E124205
|
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: Taras Bulba (character) | Statement: [Taras Bulba, mainCharacter, Taras Bulba (character)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taras Bulba (character) Context triple: [Taras Bulba, mainCharacter, Taras Bulba (character)]
-
A.
Vasyl
Vasyl is a common Ukrainian male given name, equivalent to Basil in English.
-
B.
Taras
Taras is the ancient Greek city in southern Italy that later became known by its Roman name Tarentum.
-
C.
Taras Bulba
chosen
Taras Bulba is a historical novella by Nikolai Gogol that portrays the fierce, tragic lives and battles of Ukrainian Cossacks in the 16th–17th centuries.
-
D.
Mykola
Mykola is the Ukrainian form of the given name Nicholas, commonly used in Ukraine and among Ukrainian communities.
-
E.
Vadym
Vadym is a masculine given name of Slavic origin, commonly used in Ukraine and other Eastern European countries.
- 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_69c00824643c81909ffdb888a2d35189 |
completed | March 22, 2026, 3:17 p.m. |
| NER | Named-entity recognition | batch_69c02283bb248190b29ac6255c78c5ec |
completed | March 22, 2026, 5:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04d7456408190962c476f2848927e |
completed | March 22, 2026, 8:13 p.m. |
Created at: March 22, 2026, 3:41 p.m.