Triple
T11299826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Firemen’s Ball |
E267553
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Jiří Šlitr |
E926905
|
NE FINISHED |
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 Šlitr | Statement: [The Firemen’s Ball, musicBy, Jiří Šlitr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jiří Šlitr Context triple: [The Firemen’s Ball, musicBy, Jiří Šlitr]
-
A.
Jiří Šlitr
chosen
Jiří Šlitr was a Czech composer, pianist, singer, and actor best known for his influential work in Czech popular music and theater during the 1960s, particularly in collaboration with Jiří Suchý at the Semafor Theatre.
-
B.
Josef Šebek
Josef Šebek is an actor known for appearing in the classic Czech New Wave film "A Blonde in Love."
-
C.
Jan Stráský
Jan Stráský was a Czech politician who served in top governmental roles during the final years of Czechoslovakia and later in the Czech Republic.
-
D.
Karel Šimka
Karel Šimka is a Czech lawyer and judge who serves as the president of the Supreme Administrative Court of the Czech Republic.
-
E.
Oldřich Nejedlý
Oldřich Nejedlý was a renowned Czech footballer of the 1930s, celebrated as one of Europe’s most prolific forwards of his era.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aac993a08190a6f36445ebaf9a43 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9a4aad4819097384e1b591be2e3 |
completed | April 9, 2026, 6:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ee861f89b48190b06fba51475497e6 |
completed | April 26, 2026, 9:39 p.m. |
Created at: April 8, 2026, 9:32 p.m.