Triple
T15690867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Léon Blum |
E380323
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Thérèse Blum |
E380323
|
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: Thérèse Blum | Statement: [Léon Blum, spouse, Thérèse Blum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thérèse Blum Context triple: [Léon Blum, spouse, Thérèse Blum]
-
A.
Thérèse Blum
chosen
Thérèse Blum was the wife of French socialist statesman and three-time Prime Minister Léon Blum.
-
B.
Dorothée Blanck
Dorothée Blanck was a French actress best known for her role in Agnès Varda’s influential New Wave film "Cléo from 5 to 7."
-
C.
Françoise Schein
Françoise Schein is a Belgian-born artist and architect known for large-scale public artworks, often in metro stations, that integrate human rights themes and typographic design.
-
D.
Gisèle Braunberger
Gisèle Braunberger is a French film producer known for her work on influential art-house cinema, including early films of the French New Wave.
-
E.
Brigitte Kronauer
Brigitte Kronauer was a renowned German writer celebrated for her stylistically rich, psychologically nuanced prose and numerous literary awards.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4e59988190aaf12f6a07c8f0e4 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa12713588190a888d6f6dd4290e1 |
completed | May 9, 2026, 9:03 p.m. |
Created at: April 10, 2026, 4:44 a.m.