Triple
T22716365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Guy Thing |
E561742
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Greg Glienna |
—
|
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: Greg Glienna | Statement: [A Guy Thing, screenwriter, Greg Glienna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Glienna Context triple: [A Guy Thing, screenwriter, Greg Glienna]
-
A.
Greg Glienna
chosen
Greg Glienna is an American filmmaker, screenwriter, and actor best known for creating the original characters and story that inspired the "Meet the Parents" film series.
-
B.
Greg Ganske
Greg Ganske is an American plastic surgeon and Republican politician who represented Iowa in the U.S. House of Representatives from 1995 to 2003.
-
C.
Glen Leach
Glen Leach is a musician best known as a member of the British rock band Wishbone Ash.
-
D.
Brent Gutzeit
Brent Gutzeit is an American experimental musician and sound artist known for his work in noise, drone, and electroacoustic music, as well as for co-founding the label and collective Boxmedia.
-
E.
Greg Latta
Greg Latta was an American professional football tight end who played in the World Football League and the NFL, most notably for the Chicago Bears.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790e14c88190af6acb27910ae9c1 |
completed | April 29, 2026, 3:20 a.m. |
Created at: April 17, 2026, 3:19 p.m.