Triple
T10514977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Logorama |
E248007
|
entity |
| Predicate | writtenBy |
P806
|
FINISHED |
| Object | François Alaux |
E1037386
|
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: François Alaux | Statement: [Logorama, writtenBy, François Alaux]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: François Alaux Context triple: [Logorama, writtenBy, François Alaux]
-
A.
François Alaux
chosen
François Alaux is a French filmmaker best known for co-directing the Oscar-winning animated short film "Logorama."
-
B.
Jacques Villeglé
Jacques Villeglé was a French artist best known for his torn poster collages that transformed urban street advertisements into politically and socially charged works of art.
-
C.
René Guiette
René Guiette was a Belgian painter and art critic associated with modernist movements in the early 20th century.
-
D.
Marie-Dominique Culioli
Marie-Dominique Culioli is a French woman best known as the first wife of former French president Nicolas Sarkozy.
-
E.
Louis Marie Turreau
Louis Marie Turreau was a French Revolutionary general notorious for leading the brutal "infernal columns" campaign that devastated the Vendée region during the War in the Vendée.
- 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_69d381c4aa948190942e1d803143fb0e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d509cbacb08190a446c864b97823ad |
completed | April 7, 2026, 1:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7304bc684819083ca999f283b0cb3 |
completed | May 3, 2026, 11:23 a.m. |
Created at: April 6, 2026, 12:27 p.m.