Triple
T3587924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Léon Blum |
E75954
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Jeanne Blum
Jeanne Blum was the wife of French socialist leader and three-time Prime Minister Léon Blum.
|
E371588
|
NE FINISHED |
How this triple was built (4 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: Jeanne Blum | Statement: [Léon Blum, spouse, Jeanne Blum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeanne Blum Context triple: [Léon Blum, spouse, Jeanne Blum]
-
A.
Ruth Franklin
Ruth Franklin is an American literary critic and biographer best known for her acclaimed biography of novelist Shirley Jackson.
-
B.
Brigitte Fouré
Brigitte Fouré is a French politician known for serving as the mayor of the city of Amiens.
-
C.
Georgette Leblanc
Georgette Leblanc was a French operatic soprano and actress known for her performances in symbolist works and her close association with the literary and artistic circles of the late 19th and early 20th centuries.
-
D.
Martine Franck
Martine Franck was a Belgian-born British photographer renowned for her humanist, documentary-style work and as a prominent member of the Magnum Photos agency.
-
E.
Leila Gerstein
Leila Gerstein is an American television writer and producer best known for creating the comedy-drama series "Hart of Dixie."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jeanne Blum Triple: [Léon Blum, spouse, Jeanne Blum]
Generated description
Jeanne Blum was the wife of French socialist leader and three-time Prime Minister Léon Blum.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jeanne Blum Target entity description: Jeanne Blum was the wife of French socialist leader and three-time Prime Minister Léon Blum.
-
A.
Ruth Franklin
Ruth Franklin is an American literary critic and biographer best known for her acclaimed biography of novelist Shirley Jackson.
-
B.
Brigitte Fouré
Brigitte Fouré is a French politician known for serving as the mayor of the city of Amiens.
-
C.
Georgette Leblanc
Georgette Leblanc was a French operatic soprano and actress known for her performances in symbolist works and her close association with the literary and artistic circles of the late 19th and early 20th centuries.
-
D.
Martine Franck
Martine Franck was a Belgian-born British photographer renowned for her humanist, documentary-style work and as a prominent member of the Magnum Photos agency.
-
E.
Leila Gerstein
Leila Gerstein is an American television writer and producer best known for creating the comedy-drama series "Hart of Dixie."
- F. None of above. chosen
Provenance (5 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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc13a11608190a23d76efc1b50e3c |
completed | March 8, 2026, 6:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b40304a2e08190bcf25ddaf2bc5a2a |
completed | March 13, 2026, 12:28 p.m. |
| NEDg | Description generation | batch_69b406f095488190b4543fa8008fe86c |
completed | March 13, 2026, 12:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b40872099c81909bc3531bea77f875 |
completed | March 13, 2026, 12:52 p.m. |
Created at: March 8, 2026, 3:22 p.m.