Triple
T19749702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocket Internet |
E474344
|
entity |
| Predicate | keyPerson |
P256
|
FINISHED |
| Object | Oliver Samwer |
—
|
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: Oliver Samwer | Statement: [Rocket Internet, keyPerson, Oliver Samwer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oliver Samwer Context triple: [Rocket Internet, keyPerson, Oliver Samwer]
-
A.
Oliver Samwer
chosen
Oliver Samwer is a German internet entrepreneur and investor best known as a co-founder of Rocket Internet and for building and scaling numerous online startups worldwide.
-
B.
Oliver Günther
Oliver Günther is a German computer scientist and academic who serves as the president (rector) of the University of Potsdam.
-
C.
Oliver Kassman
Oliver Kassman is a film producer known for his work on the psychological horror film "Love Lies Bleeding."
-
D.
Oliver Beene
Oliver Beene is an early-2000s American sitcom that nostalgically follows the misadventures of a quirky young boy growing up in 1960s New York.
-
E.
Oliver Korittke
Oliver Korittke is a German actor known for his roles in film and television, particularly in comedies and crime series.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529875688190952af476aa5be492 |
completed | April 20, 2026, 4:21 p.m. |
Created at: April 10, 2026, 1:47 p.m.