Triple
T15511295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brigadier Gerard |
E368714
|
entity |
| Predicate | dam |
P8736
|
FINISHED |
| Object | La Paiva |
E1160588
|
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: La Paiva | Statement: [Brigadier Gerard, dam, La Paiva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: La Paiva Context triple: [Brigadier Gerard, dam, La Paiva]
-
A.
La Paiva
chosen
La Paiva was a Thoroughbred broodmare best known as the dam of the champion racehorse Brigadier Gerard.
-
B.
Ramos de Azevedo
Ramos de Azevedo was a prominent Brazilian architect and engineer known for shaping São Paulo’s urban landscape in the late 19th and early 20th centuries.
-
C.
Engenheiro Coelho
Engenheiro Coelho is a small Brazilian municipality in the state of São Paulo, known for its rural character and integration into the economically important Campinas region.
-
D.
Dias de Oliveira
Dias de Oliveira is the family name of Brazilian actress and singer Marjorie Estiano.
-
E.
Aleijadinho
Aleijadinho was an influential 18th-century Brazilian sculptor and architect, renowned for his baroque and rococo religious works in colonial Brazil.
- 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_69d85a1794cc8190b0b428716296e63e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e04030c0208190a1931ea130075603 |
completed | April 16, 2026, 1:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3d4cf35c8190aa8d2db6dd744c3f |
completed | May 9, 2026, 1:57 p.m. |
Created at: April 10, 2026, 3:56 a.m.