Triple
T22905969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrei Evstafievich Behrs |
E568443
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Behrs |
—
|
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: Behrs | Statement: [Andrei Evstafievich Behrs, familyName, Behrs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Behrs Context triple: [Andrei Evstafievich Behrs, familyName, Behrs]
-
A.
Behrs
chosen
Behrs is the maiden surname of Sophia Tolstaya, the wife of Russian novelist Leo Tolstoy, and belongs to a Russian noble family.
-
B.
Zehrs
Zehrs is a Canadian supermarket chain operating primarily in Ontario and known for offering a wide range of groceries and household products under various national and private-label brands.
-
C.
Petit & Fritsen
Petit & Fritsen is a historic Dutch bell foundry renowned for casting church bells and carillons used in notable towers and monuments worldwide.
-
D.
Wedeco
Wedeco is a water treatment brand known for its ultraviolet (UV) disinfection and ozone oxidation technologies used in municipal and industrial applications.
-
E.
Franke
Franke is a variant form of the given name Frank, typically used as a surname or less common personal name in Germanic-speaking regions.
- 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_69e2458cd9e48190943ad2e34485d939 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1801a48948190b5f51f1d02351fc7 |
completed | April 29, 2026, 3:50 a.m. |
Created at: April 17, 2026, 3:41 p.m.