Triple
T23023112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loser |
E573222
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Thomas Sadoski |
—
|
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: Thomas Sadoski | Statement: [Loser, starring, Thomas Sadoski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Sadoski Context triple: [Loser, starring, Thomas Sadoski]
-
A.
Thomas Sadoski
chosen
Thomas Sadoski is an American actor known for his roles in television series like "The Newsroom" and films such as "John Wick" and "Wild."
-
B.
Larry Gura
Larry Gura is a former Major League Baseball left-handed pitcher best known for his successful tenure with the Kansas City Royals during the 1970s and early 1980s.
-
C.
Kirby Reed
Kirby Reed is a sharp-witted, horror-savvy teenager and fan-favorite character from the Scream film franchise.
-
D.
Mike Vogel
Mike Vogel is an American actor known for his roles in films like "Cloverfield" and "The Help" as well as TV series such as "Under the Dome."
-
E.
Michael J. Hopkins
Michael J. Hopkins is an American mathematician renowned for his influential work in algebraic topology and homotopy theory.
- 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_69e245b821008190b0e09cb02092aae1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183ea23088190b2f42d9bf01514ac |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.