Triple
T19397821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thunderheart |
E485238
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | John Fusco |
—
|
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: John Fusco | Statement: [Thunderheart, screenwriter, John Fusco]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Fusco Context triple: [Thunderheart, screenwriter, John Fusco]
-
A.
John Fusco
chosen
John Fusco is an American screenwriter and producer best known for writing Western-themed films such as "Young Guns" and creating the Netflix series "Marco Polo."
-
B.
John Ferolito
John Ferolito is an American entrepreneur best known as a co-founder of the Arizona Iced Tea beverage brand.
-
C.
John DiFronzo
John DiFronzo was an American mobster who rose to become a powerful boss of the Chicago Outfit and a prominent figure in organized crime.
-
D.
Joseph Ficalora
Joseph Ficalora is a Brooklyn-based curator and community organizer best known for creating the Bushwick Collective, a prominent open-air street art gallery in New York City.
-
E.
Richard Ruccolo
Richard Ruccolo is an American actor best known for his role as Pete Dunville on the sitcom "Two Guys, a Girl and a Pizza Place."
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62574edd08190b5456108d5e3907e |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 10, 2026, 1:36 p.m.