Triple
T21641962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candy (1968 film) |
E534107
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Elsa Martinelli |
—
|
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: Elsa Martinelli | Statement: [Candy (1968 film), stars, Elsa Martinelli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elsa Martinelli Context triple: [Candy (1968 film), stars, Elsa Martinelli]
-
A.
Elsa Martinelli
chosen
Elsa Martinelli was an Italian actress and fashion model known for her international film career in the 1950s and 1960s.
-
B.
Ilsa Pucci
Ilsa Pucci is a wealthy, sophisticated widow who becomes a key benefactor and ally to Christopher Chance and his team in the action-drama TV series "Human Target."
-
C.
Elsa Mars
Elsa Mars is a fictional German expatriate and ambitious but troubled leader of a 1950s Florida freak show, portrayed by Jessica Lange in the television series American Horror Story: Freak Show.
-
D.
Elsa Walsh
Elsa Walsh is an American journalist and author known for her work at The Washington Post and The New Yorker, as well as her book "Divided Lives."
-
E.
Elsa Pataky
Elsa Pataky is a Spanish actress and model best known for her roles in the Fast & Furious film franchise and various international action and thriller movies.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5392343c81909820cb0c3c6a4284 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:35 p.m.