Triple
T21380151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prostějov |
E527327
|
entity |
| Predicate | hasNotablePerson |
P304
|
FINISHED |
| Object | Otto Wichterle |
—
|
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: Otto Wichterle | Statement: [Prostějov, hasNotablePerson, Otto Wichterle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Otto Wichterle Context triple: [Prostějov, hasNotablePerson, Otto Wichterle]
-
A.
Otto Wichterle
chosen
Otto Wichterle was a Czech chemist best known for inventing soft contact lenses and pioneering the development of hydrogels.
-
B.
Josef Prem
Josef Prem was a mountaineer known for making the first recorded ascent of Nevado Sajama, the highest peak in Bolivia.
-
C.
Jaroslav Heyrovský
Jaroslav Heyrovský was a Czech chemist and Nobel laureate renowned as the founder of polarography, an electrochemical analysis method.
-
D.
Hans Waloschek
Hans Waloschek was a German architect best known for designing Hamburg’s iconic Heinrich-Hertz-Turm telecommunications tower.
-
E.
Max Slevogt
Max Slevogt was a prominent German Impressionist painter and illustrator, known for his vibrant landscapes, portraits, and book illustrations in the late 19th and early 20th centuries.
- 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_69e0b51f363c8190944000ab5523b02b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b0cdab8c8190a7eebe6e5961ee75 |
completed | April 22, 2026, 11:28 a.m. |
Created at: April 16, 2026, 5:11 p.m.