Triple
T21861651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celia Franca |
E539777
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Celia Franca |
—
|
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: Celia Franca | Statement: [Celia Franca, name, Celia Franca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Celia Franca Context triple: [Celia Franca, name, Celia Franca]
-
A.
Celia Franca
chosen
Celia Franca was a British-Canadian dancer, choreographer, and artistic director who played a pivotal role in establishing professional ballet in Canada.
-
B.
Emmanuelle Castro
Emmanuelle Castro is a film editor known for her work on the French film "La Bûche."
-
C.
Isabel Sarli
Isabel Sarli was an iconic Argentine actress and sex symbol best known for her starring roles in erotic films of the 1950s–1970s directed by Armando Bó.
-
D.
Rosa Mendes
Rosa Mendes is a Canadian professional wrestler, model, and former WWE Diva best known for her tenure with WWE and appearances on the reality TV series Total Divas.
-
E.
Fernanda Henry
Fernanda Henry was the wife of American department store heir and philanthropist Rodman Wanamaker.
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d63ae3708190b7ee04c1487713c9 |
completed | April 28, 2026, 3:46 p.m. |
Created at: April 16, 2026, 6:56 p.m.