Triple
T22397397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horst Dassler |
E553670
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Horst Dassler |
—
|
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: Horst Dassler | Statement: [Horst Dassler, name, Horst Dassler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Horst Dassler Context triple: [Horst Dassler, name, Horst Dassler]
-
A.
Horst Dassler
chosen
Horst Dassler was a German businessman and sports marketing pioneer who led Adidas and founded the sports marketing agency ISL, playing a key role in shaping modern sports sponsorship.
-
B.
Rudolf Dassler
Rudolf Dassler was a German entrepreneur best known as the founder of the sportswear company Puma.
-
C.
Adolf Dassler
Adolf Dassler was a German cobbler and entrepreneur who became famous as the founder of the global sportswear brand Adidas.
-
D.
Werner Scholl
Werner Scholl was the younger brother of Hans and Sophie Scholl, associated with the White Rose resistance circle in Nazi Germany.
-
E.
Karl Mayer
Karl Mayer is a fictional character from the television series "Desperate Housewives," known as Susan Mayer's ex-husband.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1585f67108190b8d3f23eaa0ed120 |
completed | April 29, 2026, 1:01 a.m. |
Created at: April 16, 2026, 8:45 p.m.