Triple
T20906960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irma Santos |
E514827
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Irma Santos |
—
|
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: Irma Santos | Statement: [Irma Santos, name, Irma Santos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irma Santos Context triple: [Irma Santos, name, Irma Santos]
-
A.
Irma Santos
chosen
Irma Santos is best known as the wife of influential Cuban-American businessman and anti-Castro activist Jorge Mas Canosa.
-
B.
Rosita Farisi
Rosita Farisi is a Victorian-era companion-like character who assists the Doctor in the 2008 "Doctor Who" Christmas special "The Next Doctor."
-
C.
Maria Vargas
Maria Vargas is the charismatic Spanish dancer-turned-film-star at the center of the 1954 drama "The Barefoot Contessa," whose rise to fame and tragic fate drive the film's narrative.
-
D.
Yolanda Ramos
Yolanda Ramos is a Spanish actress and comedian known for her work in television, film, and theater, particularly in Spanish comedy shows and movies.
-
E.
Amada Cruz
Amada Cruz is an American museum director and arts administrator known for leading major art institutions, including serving as director of the Seattle Art Museum.
- 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e900ee7881909ab1046b40dca486 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.