Triple
T17956856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jiří Orten |
E448972
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Jiří Orten |
—
|
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: Jiří Orten | Statement: [Jiří Orten, name, Jiří Orten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jiří Orten Context triple: [Jiří Orten, name, Jiří Orten]
-
A.
Jiří Orten
chosen
Jiří Orten was a Czech Jewish poet known for his lyrical, introspective verse and his tragic early death during World War II.
-
B.
Jiří Sequens
Jiří Sequens was a Czech film and television director best known for his politically charged dramas and crime series produced during the communist era in Czechoslovakia.
-
C.
Jaroslav Ježek
Jaroslav Ježek was a Czech composer, pianist, and conductor best known for his jazz-influenced classical and popular music, particularly his collaborations with the avant-garde Liberated Theatre in interwar Czechoslovakia.
-
D.
Jiří Korn
Jiří Korn is a Czech singer, actor, and entertainer known for his long and versatile career in pop music, musical theatre, and television.
-
E.
Josef Šebek
Josef Šebek is an actor known for appearing in the classic Czech New Wave film "A Blonde in Love."
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afb0afe08190964e771ec632fa1e |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 10:21 a.m.