Triple
T17847741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cap Corse |
E445707
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Brando |
—
|
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: Brando | Statement: [Cap Corse, hasSettlement, Brando]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brando Context triple: [Cap Corse, hasSettlement, Brando]
-
A.
Brando
chosen
Brando is a coastal commune on the island of Corsica in southeastern France, known for its picturesque villages and Mediterranean scenery.
-
B.
The Brando
The Brando is an exclusive luxury eco-resort on the private Polynesian atoll of Tetiaroa, once owned by actor Marlon Brando.
-
C.
Marlon Brando Sr.
Marlon Brando Sr. was an American salesman and the father of legendary actor Marlon Brando.
-
D.
Marlon Brando
Marlon Brando was an influential American actor widely regarded as one of the greatest performers in cinema history, known for his groundbreaking method acting and iconic roles in films such as "A Streetcar Named Desire," "On the Waterfront," and "The Godfather."
-
E.
Frances Brando
Frances Brando was a sibling of legendary American actor Marlon Brando and a member of the Brando family.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ffc5fec8190adc66f7b0e264d5f |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:16 a.m.