Triple
T16367745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | O Primo Basílio |
E397478
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Luísa |
E44829
|
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: Luísa | Statement: [O Primo Basílio, mainCharacter, Luísa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luísa Context triple: [O Primo Basílio, mainCharacter, Luísa]
-
A.
Luisa
chosen
Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
-
B.
Eugênia
Eugênia is a Portuguese given name, equivalent to Eugenia, commonly used in Brazil and other Lusophone countries.
-
C.
Margarida
Margarida is a given name, commonly used in Portuguese and Catalan, that corresponds to the English name Margaret.
-
D.
Maria Francesca
Maria Francesca of Savoy was an 18th-century Italian princess of the House of Savoy who became Landgravine of Hesse-Rotenburg through marriage.
-
E.
Isabella
Isabella was a Polish princess of the Jagiellonian dynasty who became Queen consort of Hungary in the 16th century.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff3f0694819097faa1c1447a9e97 |
completed | April 18, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dc29f088190ba5d69ff3c12a251 |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:08 a.m.