Triple
T12235073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marjorie Nelson |
E291568
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Howard Da Silva |
E22207
|
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: Howard Da Silva | Statement: [Marjorie Nelson, spouse, Howard Da Silva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Da Silva Context triple: [Marjorie Nelson, spouse, Howard Da Silva]
-
A.
Howard Da Silva
chosen
Howard Da Silva was an American character actor and singer known for his work on Broadway and in film, including notable roles in classic musicals and dramas.
-
B.
Jackson Silva
Jackson Silva is a fictional jockey who serves as the central protagonist in a narrative focused on horse racing.
-
C.
Anthony Santos
Anthony Santos, better known as Romeo Santos, is an American singer, songwriter, and former lead vocalist of the bachata group Aventura, widely acclaimed as the "King of Bachata."
-
D.
Tony Almeida
Tony Almeida is a key fictional Counter Terrorist Unit agent in the television series "24," known for his complex loyalties and evolving role across multiple seasons.
-
E.
Wendell Ramos
Wendell Ramos is a Filipino actor and comedian best known for his work on television sitcoms and sketch comedy shows.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cb2892c81909a97b3ad6ec2c21b |
completed | April 10, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60aaf7b348190865a6a1b6de51753 |
completed | May 2, 2026, 2:31 p.m. |
Created at: April 8, 2026, 9:51 p.m.