Triple
T14080828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Get Stoned |
E338860
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Austin Winkler |
E338867
|
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: Austin Winkler | Statement: [Get Stoned, writer, Austin Winkler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Austin Winkler Context triple: [Get Stoned, writer, Austin Winkler]
-
A.
Austin Winkler
chosen
Austin Winkler is an American rock singer best known as the former lead vocalist and founding member of the band Hinder.
-
B.
Ryan Dusick
Ryan Dusick is an American musician best known as the original drummer and a founding member of the pop rock band Maroon 5.
-
C.
Nathan Lind
Nathan Lind is a geologist and former Monarch scientist in the MonsterVerse franchise who helps orchestrate the expedition into the Hollow Earth in "Godzilla vs. Kong."
-
D.
Aaron Sisson
Aaron Sisson is the discontented, flute-playing coal miner and central figure in D. H. Lawrence’s novel "Aaron’s Rod," whose search for personal freedom and identity drives the narrative.
-
E.
Adam Bohling
Adam Bohling is a British film producer known for his work on high-profile action and genre films, including the Kingsman series.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0a175a48190b596ea4cf917e80e |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:21 p.m.