Triple
T20745539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mashed Potato dance |
E510573
|
entity |
| Predicate | typicalUpperBody |
P105236
|
FINISHED |
| Object | relatively still torso |
—
|
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: relatively still torso | Statement: [Mashed Potato dance, typicalUpperBody, relatively still torso]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalUpperBody Context triple: [Mashed Potato dance, typicalUpperBody, relatively still torso]
-
A.
upperBody
Indicates that one entity represents or corresponds to the upper body portion of another entity.
-
B.
typicalBodyPart
chosen
Indicates that one entity is a body part that is characteristically or normally associated with another entity.
-
C.
typicalBodyType
Indicates that one entity is the usual or characteristic body type associated with another entity.
-
D.
parentBodyType
Indicates that one entity has a body type that serves as the parent or base classification from which another entity's body type is derived or organized.
-
E.
highestBody
Indicates that one entity is the tallest or most elevated body (e.g., physical object, celestial body, or structural component) relative to a specified set or context.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c212b744819089bc1d47a020bd61 |
completed | April 21, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c0509608819080cdbf47fcddfe36 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:33 p.m.