Triple
T22883028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bea |
E567525
|
entity |
| Predicate | spellingVariantOf |
P457
|
FINISHED |
| Object | Béa |
—
|
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: Béa | Statement: [Bea, spellingVariantOf, Béa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Béa Context triple: [Bea, spellingVariantOf, Béa]
-
A.
Nelly Roussel
Nelly Roussel was a pioneering French feminist, neo-Malthusian activist, and orator known for her advocacy of birth control, women’s rights, and social reform in the early 20th century.
-
B.
Madeleine Barbulée
Madeleine Barbulée was a French character actress known for her numerous supporting roles in mid-20th-century French cinema and television.
-
C.
Josette du Pres
Josette du Pres is a tragic, ghostly heroine from the gothic soap opera "Dark Shadows," remembered as the great love of vampire Barnabas Collins.
-
D.
Léa
chosen
Léa is a French feminine given name commonly used in Francophone countries.
-
E.
Paula Bélier
Paula Bélier is the teenage protagonist of the French film "La Famille Bélier," known for being the only hearing member of her deaf family and discovering her talent for singing.
- 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_69e2458a92ec81908fc1cd5f6407d2ab |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f5dab048190a09c725dad123472 |
completed | April 29, 2026, 3:47 a.m. |
Created at: April 17, 2026, 3:39 p.m.