Triple
T18996876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karl Ziegler |
E464837
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Ziegler |
—
|
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: Ziegler | Statement: [Karl Ziegler, familyName, Ziegler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ziegler Context triple: [Karl Ziegler, familyName, Ziegler]
-
A.
Ziegler
chosen
Ziegler is a German-origin surname borne by various notable individuals across fields such as the arts, sciences, and public life.
-
B.
Zierer
Zierer is a German amusement ride manufacturer known for producing family-friendly roller coasters and classic flat rides for theme parks worldwide.
-
C.
Rigler
Rigler is a surname most notably associated with Cy Rigler, an early 20th-century American Major League Baseball umpire.
-
D.
Kugler
Kugler is a German-language surname borne by various notable individuals across fields such as history, the arts, and public life.
-
E.
Hilberseimer
Hilberseimer is the surname of Ludwig Hilberseimer, a German-American architect and urban planner known for his influential modernist city planning theories.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6826464819080ff0e0ffa5cc25e |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.