Triple
T19200124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Twistin' the Night Away |
E470082
|
entity |
| Predicate | danceTheme |
P103855
|
FINISHED |
| Object | twist dancing |
—
|
LITERAL 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: twist dancing | Statement: [Twistin' the Night Away, danceTheme, twist dancing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: danceTheme Context triple: [Twistin' the Night Away, danceTheme, twist dancing]
-
A.
danceFeature
chosen
Indicates that one entity serves as a notable characteristic, element, or attribute of a dance or dancing-related activity.
-
B.
danceShow
Indicates that one entity presents or performs a dance-related show or performance for another or for an audience.
-
C.
danceSceneInspired
Indicates that one dance scene is creatively influenced or modeled after another source, such as a different scene, style, or performance.
-
D.
danceProp
Indicates that one entity is used or involved as a prop in another entity’s dance performance or dancing activity.
-
E.
danceBackground
Indicates that one entity serves as the background or setting for another entity’s dancing activity.
- F. None of above.
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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f9967ac081909106aa5ea447e94d |
completed | April 20, 2026, 10:01 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bc158081908307dab01d9478c6 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:07 p.m.