Triple
T9140118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filipa Moniz Perestrelo |
E219302
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Filipa |
E42364
|
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: Filipa | Statement: [Filipa Moniz Perestrelo, givenName, Filipa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Filipa Context triple: [Filipa Moniz Perestrelo, givenName, Filipa]
-
A.
Filipa Moniz Perestrelo
chosen
Filipa Moniz Perestrelo was a Portuguese noblewoman from a prominent maritime family who became the wife of explorer Christopher Columbus.
-
B.
Madalena
Madalena is a neighborhood in the Brazilian city of Recife, known for its urban character and local commerce.
-
C.
Madalena
Madalena is a coastal town on the Azorean island of Pico in Portugal, known as a gateway to Mount Pico and for its wine culture and maritime heritage.
-
D.
Branca of Portugal
Branca of Portugal was a 15th-century Portuguese infanta of the House of Aviz, known primarily as a daughter of King John I of Portugal and sister of Peter, Duke of Coimbra.
-
E.
Ana Pinho
Ana Pinho is the wife of Portuguese professional footballer Bruno Fernandes.
- 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_69ca83e012288190a5771058adbaabd2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8f2537881908956a9b0516e2d49 |
completed | April 1, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0545584e08190bda111f2c6163a4a |
completed | April 3, 2026, 11:59 p.m. |
Created at: March 30, 2026, 7:19 p.m.