Triple
T22633447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 99 francs |
E558614
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
Jan Kounen
Jan Kounen is a French film director known for his visually stylized, often satirical and psychedelic works in both cinema and advertising.
|
E1547304
|
NE FINISHED |
How this triple was built (4 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 Kounen | Statement: [99 francs, director, Jan Kounen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Kounen Context triple: [99 francs, director, Jan Kounen]
-
A.
Jan Kotěra
Jan Kotěra was a pioneering Czech architect and key figure of early modern architecture in Central Europe, known for transitioning from Art Nouveau to functionalist and modernist styles.
-
B.
Jan Svoboda
Jan Svoboda is a Czech name shared by several notable individuals, including figures in fields such as photography, science, and sports.
-
C.
Jan Fischer
Jan Fischer is a Czech economist and non-partisan politician who served as the prime minister of the Czech Republic in a caretaker government from 2009 to 2010.
-
D.
Tomas Jurco
Tomas Jurco is a Slovak professional ice hockey forward who has played in the NHL and internationally for Slovakia.
-
E.
Jan Holoubek
Jan Holoubek is a Polish cinematographer and film director known for his work in contemporary Polish cinema and television.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jan Kounen Triple: [99 francs, director, Jan Kounen]
Generated description
Jan Kounen is a French film director known for his visually stylized, often satirical and psychedelic works in both cinema and advertising.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jan Kounen Target entity description: Jan Kounen is a French film director known for his visually stylized, often satirical and psychedelic works in both cinema and advertising.
-
A.
Jan Kotěra
Jan Kotěra was a pioneering Czech architect and key figure of early modern architecture in Central Europe, known for transitioning from Art Nouveau to functionalist and modernist styles.
-
B.
Jan Svoboda
Jan Svoboda is a Czech name shared by several notable individuals, including figures in fields such as photography, science, and sports.
-
C.
Jan Fischer
Jan Fischer is a Czech economist and non-partisan politician who served as the prime minister of the Czech Republic in a caretaker government from 2009 to 2010.
-
D.
Tomas Jurco
Tomas Jurco is a Slovak professional ice hockey forward who has played in the NHL and internationally for Slovakia.
-
E.
Jan Holoubek
Jan Holoubek is a Polish cinematographer and film director known for his work in contemporary Polish cinema and television.
- F. None of above. chosen
Provenance (5 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1700be10c8190830393fdbec1033d |
completed | April 29, 2026, 2:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b585b10688190bcc215e55add9ed1 |
completed | May 18, 2026, 6:20 p.m. |
| NEDg | Description generation | batch_6a0b6f5b85548190bd54f5a13dd27c5d |
completed | May 18, 2026, 7:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b706cba28819091d40e7832e61f97 |
completed | May 18, 2026, 8:02 p.m. |
Created at: April 17, 2026, 3:03 p.m.