Triple
T15922373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amaury family |
E386122
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Philippe Amaury |
E386118
|
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: Philippe Amaury | Statement: [Amaury family, foundedBy, Philippe Amaury]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philippe Amaury Context triple: [Amaury family, foundedBy, Philippe Amaury]
-
A.
Philippe Amaury
chosen
Philippe Amaury was a French media entrepreneur best known as the founder of the Amaury media group, which owns major sports and news publications such as L'Équipe and Le Parisien.
-
B.
Franck Massard
Franck Massard is a French local politician who serves as the mayor of the commune of Ambilly in the Haute-Savoie department of eastern France.
-
C.
Philippe Gaudin
Philippe Gaudin is a French politician who serves as the mayor of the suburban Parisian commune of Villeneuve-Saint-Georges.
-
D.
Christophe Fouquet
Christophe Fouquet is a French business executive and semiconductor industry leader who serves as the chief executive officer of Dutch lithography equipment manufacturer ASML.
-
E.
Stéphane Roche
Stéphane Roche is an editor known for his work on the publication "The Voices."
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156825b1881908477ec93cc7b5f02 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb5aba70c8190a74c45bce6f9b782 |
completed | May 9, 2026, 10:31 p.m. |
Created at: April 10, 2026, 4:52 a.m.