Triple
T16712130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qwant |
E406133
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Jean-Manuel Rozan
Jean-Manuel Rozan is a French entrepreneur best known as a co-founder of the privacy-focused search engine Qwant.
|
E1229519
|
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: Jean-Manuel Rozan | Statement: [Qwant, foundedBy, Jean-Manuel Rozan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Manuel Rozan Context triple: [Qwant, foundedBy, Jean-Manuel Rozan]
-
A.
Christophe Masle
Christophe Masle is a French racehorse breeder best known for breeding the legendary National Hunt champion Sprinter Sacre.
-
B.
Thomas Ravier
Thomas Ravier is a French politician who serves as the mayor of the town of Villefranche-sur-Saône.
-
C.
Philippe Gille
Philippe Gille was a 19th-century French librettist and journalist best known for writing opera librettos, often in collaboration with prominent composers and fellow writers.
-
D.
Thierry Boutard
Thierry Boutard is a French local politician who serves as the mayor of the town of Amboise in central France.
-
E.
Michel Seydoux
Michel Seydoux is a French film producer best known for backing ambitious auteur projects, including Alejandro Jodorowsky’s legendary unmade adaptation of "Dune."
- 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: Jean-Manuel Rozan Triple: [Qwant, foundedBy, Jean-Manuel Rozan]
Generated description
Jean-Manuel Rozan is a French entrepreneur best known as a co-founder of the privacy-focused search engine Qwant.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jean-Manuel Rozan Target entity description: Jean-Manuel Rozan is a French entrepreneur best known as a co-founder of the privacy-focused search engine Qwant.
-
A.
Christophe Masle
Christophe Masle is a French racehorse breeder best known for breeding the legendary National Hunt champion Sprinter Sacre.
-
B.
Thomas Ravier
Thomas Ravier is a French politician who serves as the mayor of the town of Villefranche-sur-Saône.
-
C.
Philippe Gille
Philippe Gille was a 19th-century French librettist and journalist best known for writing opera librettos, often in collaboration with prominent composers and fellow writers.
-
D.
Thierry Boutard
Thierry Boutard is a French local politician who serves as the mayor of the town of Amboise in central France.
-
E.
Michel Seydoux
Michel Seydoux is a French film producer best known for backing ambitious auteur projects, including Alejandro Jodorowsky’s legendary unmade adaptation of "Dune."
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e386530d9c8190b91ec3aac7dc2518 |
completed | April 18, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091a95180819099abd50dd153e229 |
completed | May 10, 2026, 2:09 p.m. |
| NEDg | Description generation | batch_6a00925fda608190b3674bd5e9ca6bf5 |
completed | May 10, 2026, 2:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00939075d88190a63cdd942eb3fea8 |
completed | May 10, 2026, 2:17 p.m. |
Created at: April 10, 2026, 5:20 a.m.