Triple
T19456348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ônibus 174 |
E486741
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Marcos Prado |
—
|
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: Marcos Prado | Statement: [Ônibus 174, producer, Marcos Prado]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcos Prado Context triple: [Ônibus 174, producer, Marcos Prado]
-
A.
Marcos Prado
chosen
Marcos Prado is a Brazilian film producer and director known for his work on acclaimed documentaries and socially engaged cinema.
-
B.
Nicolás López
Nicolás López is a Chilean filmmaker and screenwriter known for writing and directing popular Spanish-language comedies and genre films.
-
C.
Guillermo Estrella
Guillermo Estrella is an actor best known for his role in Alejandro González Iñárritu’s acclaimed drama film "Biutiful."
-
D.
Leandro Valle
Leandro Valle was a 19th-century Mexican military officer and liberal politician known for his role in the Reform War and his support of President Benito Juárez.
-
E.
Fernando Bautista
Fernando Bautista is a Filipino educator and entrepreneur best known for establishing the University of Baguio, a major private university in Baguio City, Philippines.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633c4088881908f23f25a82a513f6 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.