Triple
T20361091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spun |
E496781
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Spun |
—
|
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: Spun | Statement: [Spun, title, Spun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Spun Context triple: [Spun, title, Spun]
-
A.
Spun
chosen
Spun is a darkly comic 2002 crime film about methamphetamine addicts, directed by Jonas Åkerlund and featuring Jason Schwartzman in a leading role.
-
B.
Spinning Out
Spinning Out is a Netflix drama series about a competitive figure skater struggling with mental illness, family dynamics, and the pressures of elite sport.
-
C.
Spinnerette
Spinnerette is an alternative rock project fronted by Brody Dalle, known for its gritty, punk-influenced sound and ties to the Los Angeles rock scene.
-
D.
Hard Spun
Hard Spun is an American Thoroughbred racehorse best known for his strong performances in the 2007 Triple Crown series and as a successful sire of multiple graded stakes winners.
-
E.
Spin
Spin is a line of Acer laptops known for their 2-in-1 convertible designs with 360-degree hinges and touchscreen displays.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786de5988190827584358c9db147 |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:25 a.m.