Triple
T14907896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Honoré Fragonard |
E371183
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Jean-Honoré |
E371183
|
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: Jean-Honoré | Statement: [Jean-Honoré Fragonard, givenName, Jean-Honoré]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Honoré Context triple: [Jean-Honoré Fragonard, givenName, Jean-Honoré]
-
A.
Jean-Honoré
chosen
Jean-Honoré is the given name of the renowned French Rococo painter Jean-Honoré Fragonard.
-
B.
Jean-Jacques-Marie Huvé
Jean-Jacques-Marie Huvé was a 19th-century French architect best known for completing Paris’s neoclassical church of La Madeleine.
-
C.
Louis-Hector
Louis-Hector is the given first name of the renowned French Romantic composer Hector Berlioz.
-
D.
Pierre-Étienne
Pierre-Étienne is a French masculine given name, often associated with notable historical and political figures in France.
-
E.
Ludovic-Napoléon Lepic
Ludovic-Napoléon Lepic was a 19th-century French painter, printmaker, and archaeologist known for his association with the Impressionists and his innovative etching techniques.
- 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_69d85cc7ea3481908228b5acb7d06f12 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded61b3c808190b4f6df4e5cb401ad |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe968a17188190bced83ed1006e020 |
completed | May 9, 2026, 2:06 a.m. |
Created at: April 10, 2026, 2:23 a.m.