Triple
T22689745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dany Saval |
E561018
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Dany Saval |
—
|
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: Dany Saval | Statement: [Dany Saval, name, Dany Saval]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dany Saval Context triple: [Dany Saval, name, Dany Saval]
-
A.
Dany Saval
chosen
Dany Saval is a French actress known for her film and television roles in the 1950s and 1960s.
-
B.
Alain de la Mata
Alain de la Mata is a film producer best known for his work on the 2013 musical drama "Sunshine on Leith."
-
C.
Juan Vigón
Juan Vigón was a Spanish military officer and politician who became a prominent general under Francisco Franco and played a key role in organizing the Nationalist war effort during the Spanish Civil War.
-
D.
Ernest Colas
Ernest Colas is an entrepreneur best known as the founder and namesake of the Colas company.
-
E.
Josué de la Place
Josué de la Place was a 17th-century French Reformed theologian known for his influential work on the doctrine of mediate imputation and his role in shaping Protestant scholastic thought.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789a1fd08190bce5fa0babe695d3 |
completed | April 29, 2026, 3:18 a.m. |
Created at: April 17, 2026, 3:13 p.m.