Triple
T13429677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petr Uhl |
E313574
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Petr Uhl |
E313574
|
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: Petr Uhl | Statement: [Petr Uhl, name, Petr Uhl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petr Uhl Context triple: [Petr Uhl, name, Petr Uhl]
-
A.
Petr Uhl
chosen
Petr Uhl was a Czech journalist, dissident, and human rights activist who played a prominent role in the Czechoslovak opposition to communist rule.
-
B.
Petr Zenkl
Petr Zenkl was a prominent Czech politician and anti-communist leader who served as mayor of Prague and later as a leading figure of the Czechoslovak government-in-exile.
-
C.
Viktor Pospíšil
Viktor Pospíšil is a conductor and music director known for his leadership at the Staatsoper Stuttgart.
-
D.
Miroslav Ondříček
Miroslav Ondříček was a renowned Czech cinematographer known for his collaborations with director Miloš Forman on films such as "Amadeus" and "Ragtime."
-
E.
Miroslav Holeček
Miroslav Holeček is a Czech academic and university administrator who has served as rector of the University of West Bohemia.
- 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_69d806ad0c44819088833ae1ec9e9690 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaed304ac8190a8021f749de8164c |
completed | April 12, 2026, 2:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce5ecad88190b7c8236969d9abc7 |
completed | May 3, 2026, 10:38 p.m. |
Created at: April 9, 2026, 9:40 p.m.