Triple
T17854899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maria Victoria Henao |
E445905
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Maria Victoria Henao |
—
|
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: Maria Victoria Henao | Statement: [Maria Victoria Henao, name, Maria Victoria Henao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maria Victoria Henao Context triple: [Maria Victoria Henao, name, Maria Victoria Henao]
-
A.
Maria Victoria Henao
chosen
Maria Victoria Henao is the widow of Colombian drug lord Pablo Escobar, known for her long marriage to him and later life in relative obscurity under an assumed identity.
-
B.
Isabel Blandón
Isabel Blandón is best known as the wife of Cuban revolutionary figure Camilo Cienfuegos.
-
C.
Luna Aristizábal Martínez
Luna Aristizábal Martínez is a daughter of Colombian singer-songwriter Juanes.
-
D.
Ximena Restrepo
Ximena Restrepo is a former Colombian sprinter and Olympic bronze medalist who became a prominent athletics administrator and leader in the sport’s global governance.
-
E.
Patricia Velásquez
Patricia Velásquez is a Venezuelan actress and model best known for her roles in films such as The Mummy franchise and various international television and movie productions.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4978af9b0819091780281344f5352 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.