Triple
T21323270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friedrich Weiss |
E525678
|
entity |
| Predicate | hasSurnameVariant |
P457
|
FINISHED |
| Object | Weiß |
—
|
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: Weiß | Statement: [Friedrich Weiss, hasSurnameVariant, Weiß]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Weiß Context triple: [Friedrich Weiss, hasSurnameVariant, Weiß]
-
A.
Weiß
chosen
Weiß is a German surname commonly borne by individuals of German-speaking origin.
-
B.
Бяла
Бяла is a small Bulgarian town known for its location near the Black Sea coast and its mix of historical and seaside tourism attractions.
-
C.
Holzweißig
Holzweißig is a former municipality in Saxony-Anhalt, Germany, that now forms part of the industrial town of Bitterfeld-Wolfen.
-
D.
Bianco
Bianco is an Italian surname commonly associated with individuals of Italian heritage, including the artist Enrico Bianco.
-
E.
Witte
Witte is a surname most notably associated with Edwin E. Witte, an American economist often called the “father of Social Security” for his key role in shaping U.S. social welfare policy.
- 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_69e0b51ad810819098c12392c8e55f6c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e77ed572548190bd71ef690fc7befe |
completed | April 21, 2026, 1:42 p.m. |
Created at: April 16, 2026, 4:40 p.m.