Triple
T17788127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympia |
E444074
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Paul Falkenberg |
—
|
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: Paul Falkenberg | Statement: [Olympia, editor, Paul Falkenberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Falkenberg Context triple: [Olympia, editor, Paul Falkenberg]
-
A.
Paul Falkenberg
chosen
Paul Falkenberg was a German film editor best known for his influential work on Leni Riefenstahl’s documentary "Olympia."
-
B.
Conrad Falkenberg
Conrad Falkenberg was a medieval Swedish statesman who served as the kingdom’s highest legal and political official during his tenure as Lord High Chancellor.
-
C.
Paul Friedrichs
Paul Friedrichs is a former East German motocross racer who became a three-time FIM 500cc Motocross World Champion in the late 1960s.
-
D.
Robert von Bahr
Robert von Bahr is a Swedish music executive best known as the founder and longtime leader of the classical music label BIS Records, recognized for its high-quality and often pioneering recordings.
-
E.
Paul Schulze
Paul Schulze is an American character actor best known for his roles in television series such as "Nurse Jackie," "The Sopranos," and "24."
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48794542c8190b049bce6e28c9f3a |
completed | April 19, 2026, 7:43 a.m. |
Created at: April 10, 2026, 10:12 a.m.