Triple
T19729520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joan Bruna |
E473813
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object | Stéphane Mallat |
—
|
NE NERFINISHED |
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: Stéphane Mallat | Statement: [Joan Bruna, coAuthorWith, Stéphane Mallat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stéphane Mallat Context triple: [Joan Bruna, coAuthorWith, Stéphane Mallat]
-
A.
Stéphane Mallat
chosen
Stéphane Mallat is a French mathematician and computer scientist renowned for his pioneering work in wavelet theory, signal processing, and their applications to image analysis and machine learning.
-
B.
Samuel Le Bihan
Samuel Le Bihan is a French actor known for his roles in films such as "Brotherhood of the Wolf" and various French thrillers and dramas.
-
C.
Jean-Marc Valin
Jean-Marc Valin is a Canadian computer scientist and audio codec engineer best known for creating the Speex and Opus audio compression formats.
-
D.
André Thirion
André Thirion was a French writer, political activist, and prominent member of the Parisian Surrealist movement in the early 20th century.
-
E.
Andrew Donoho
Andrew Donoho is a contemporary American music video director known for his visually inventive work with prominent hip-hop and pop artists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649fb27c48190893bfbc1018f12e2 |
completed | April 20, 2026, 3:44 p.m. |
Created at: April 10, 2026, 1:47 p.m.