Triple
T16093243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fajã d’Água |
E390413
|
entity |
| Predicate | locatedOnIsland |
P970
|
FINISHED |
| Object | Brava |
E93086
|
NE FINISHED |
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: Brava | Statement: [Fajã d’Água, locatedOnIsland, Brava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brava Context triple: [Fajã d’Água, locatedOnIsland, Brava]
-
A.
Brava
chosen
Brava is a small, mountainous island in the Cape Verde archipelago known for its lush vegetation, volcanic landscapes, and traditional Creole culture.
-
B.
Wonderbra
Wonderbra is a famous push-up bra brand known for its cleavage-enhancing lingerie and iconic advertising campaigns.
-
C.
Bravo
Bravo is an American cable television network best known for its reality TV programming and pop culture–focused entertainment.
-
D.
Bravo
Bravo is a company best known for operating the Bravo app, a platform that facilitates cashless tipping and payments.
-
E.
Bright Victory
Bright Victory is a 1951 American drama film about a blinded World War II soldier’s struggle to adapt to his disability and rebuild his life.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1858ed09881909bde122971d95753 |
completed | April 17, 2026, 12:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000ec4d9808190a3d1bfc8f3d73168 |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 4:59 a.m.