Triple
T20029031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ever After |
E495070
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Mireille Soria |
—
|
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: Mireille Soria | Statement: [Ever After, producer, Mireille Soria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mireille Soria Context triple: [Ever After, producer, Mireille Soria]
-
A.
Mireille Soria
chosen
Mireille Soria is a film producer best known for her work on major animated features at DreamWorks Animation.
-
B.
Yvonne Monlaur
Yvonne Monlaur was a French actress best known for her roles in 1960s Hammer horror films.
-
C.
Sylvie Kosloff
Sylvie Kosloff is a fictional character known primarily as the mother of Iris Carrington in the soap opera "Another World."
-
D.
Françoise Rosay
Françoise Rosay was a prominent French stage and film actress known for her powerful character roles in European cinema from the 1920s through the 1950s.
-
E.
Yolande Moreau
Yolande Moreau is a Belgian actress, comedian, and filmmaker known for her acclaimed performances in French-language cinema and her distinctive blend of humor and poignancy.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e662908df081909a6c8ccf0dd90fff |
completed | April 20, 2026, 5:29 p.m. |
Created at: April 11, 2026, 3:36 p.m.