Triple
T19164938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ilha do Maio |
E469154
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Figueira Seca |
—
|
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: Figueira Seca | Statement: [Ilha do Maio, hasSettlement, Figueira Seca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Figueira Seca Context triple: [Ilha do Maio, hasSettlement, Figueira Seca]
-
A.
Figueira Seca
chosen
Figueira Seca is a small village located on the island of Maio in Cape Verde.
-
B.
Alfarrobeira
Alfarrobeira is a historical site in Portugal best known as the location of the 1449 Battle of Alfarrobeira, a pivotal conflict in Portuguese medieval history.
-
C.
Algar Seco
Algar Seco is a striking coastal rock formation and cave complex on the Algarve coast of Portugal, known for its dramatic cliffs, natural pools, and scenic ocean views.
-
D.
Frasqueira
Frasqueira is a premium category of Madeira wine denoting long-aged, high-quality vintage bottlings.
-
E.
Manzanilla
Manzanilla is a dry, pale Spanish fino-style sherry wine traditionally produced and aged in the coastal town of Sanlúcar de Barrameda.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f15e2720819084b1707497db26a2 |
completed | April 20, 2026, 9:26 a.m. |
Created at: April 10, 2026, 12:06 p.m.