Triple
T15609635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeanne de Casalis |
E375252
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Jeanne de Casalis |
E375252
|
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: Jeanne de Casalis | Statement: [Jeanne de Casalis, name, Jeanne de Casalis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeanne de Casalis Context triple: [Jeanne de Casalis, name, Jeanne de Casalis]
-
A.
Jeanne de Casalis
chosen
Jeanne de Casalis was a British-based actress and radio comedian, best known for her character "Mrs. Feather" and her work on stage, film, and radio in the early 20th century.
-
B.
Jeanne Claussat
Jeanne Claussat was the wife of French politician and World War II-era Prime Minister Pierre Laval.
-
C.
Jeanne de Lartigue
Jeanne de Lartigue was the French Huguenot wife of philosopher and mathematician Pierre Bayle, known primarily through her association with his life and work.
-
D.
Jeanne de Lartigue
Jeanne de Lartigue was the wife of French Enlightenment philosopher and political thinker Montesquieu.
-
E.
Jeanne d’Alcy
Jeanne d’Alcy was a pioneering French stage and film actress, best known as one of the earliest film performers and a frequent collaborator in Georges Méliès’s groundbreaking silent films.
- 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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e8024948190a6c711f2e5c2aac4 |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56d76c108190aa3cae2d7e17c301 |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 4:13 a.m.