Triple
T22210787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lena Olin |
E548937
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Casanova |
—
|
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: Casanova | Statement: [Lena Olin, notableWork, Casanova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Casanova Context triple: [Lena Olin, notableWork, Casanova]
-
A.
Casanova
chosen
Casanova is a 2005 British television drama serial written by Russell T Davies that reimagines the life and loves of the famed 18th-century adventurer Giacomo Casanova.
-
B.
Casanova
Casanova is an American rapper known for his gritty street narratives and energetic delivery, emerging from Brooklyn’s hip-hop scene in the mid-2010s.
-
C.
Casanova
Casanova is a small commune in the Haute-Corse department on the island of Corsica in France.
-
D.
Giacomo Casanova
Giacomo Casanova was an 18th-century Venetian adventurer, writer, and famed libertine whose name became synonymous with seduction and romantic intrigue.
-
E.
Don Juan
Don Juan is a studio album by Colombian reggaeton singer Maluma that showcases his blend of urban Latin, pop, and romantic themes.
- 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2bcf748190a9721f0c9ae17e70 |
completed | April 28, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:36 p.m.