Triple
T21206579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carl Schenkel |
E522600
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Carl Schenkel |
—
|
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: Carl Schenkel | Statement: [Carl Schenkel, name, Carl Schenkel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carl Schenkel Context triple: [Carl Schenkel, name, Carl Schenkel]
-
A.
Carl Schenkel
chosen
Carl Schenkel was a Swiss film director known for his work on thrillers and adventure films in both European and Hollywood cinema.
-
B.
George B. Schubauer
George B. Schubauer was an American engineer and experimental physicist known for his influential work in fluid mechanics and turbulence research.
-
C.
John H. Dietrich
John H. Dietrich was an influential American Unitarian minister and early 20th-century leader in religious humanism, known for helping to shape modern humanist thought.
-
D.
John A. Knebel
John A. Knebel is an American lawyer and government official who served as United States Secretary of Agriculture in the 1970s.
-
E.
Charles T. Brumback
Charles T. Brumback was an American media executive best known for serving as a top leader, including CEO, of the Tribune Company, the major newspaper and broadcasting conglomerate.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73435322c8190bf4156fbd14edc5c |
completed | April 21, 2026, 8:24 a.m. |
Created at: April 16, 2026, 3:20 p.m.