Triple
T19233999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Syrový |
E480944
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Jan Syrový |
—
|
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: Jan Syrový | Statement: [Syrový, hasNotableBearer, Jan Syrový]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Syrový Context triple: [Syrový, hasNotableBearer, Jan Syrový]
-
A.
Jan Syrový
chosen
Jan Syrový was a Czechoslovak army general and politician who briefly served as prime minister during the critical period following the Munich Agreement in 1938.
-
B.
Jiří Svoboda
Jiří Svoboda is a Czech film director, screenwriter, and former politician known for his socially critical films and his tenure as chairman of the Communist Party of Bohemia and Moravia in the early 1990s.
-
C.
Jaroslav Kvapil
Jaroslav Kvapil was a Czech poet, playwright, and librettist best known for writing the libretto to Antonín Dvořák’s opera "Rusalka."
-
D.
Josef Němec
Josef Němec was a 19th-century Czech customs officer best known as the husband of renowned writer Božena Němcová.
-
E.
Jan Černocký
Jan Černocký is a Czech researcher in speech and audio processing, known for his work in machine learning and his role at Brno University of Technology’s Speech@FIT group.
- 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5faeb53988190b83afee9974058c6 |
completed | April 20, 2026, 10:07 a.m. |
Created at: April 10, 2026, 1:26 p.m.