Triple
T23314534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Union of Musicians |
E590667
|
entity |
| Predicate | usesMusicFor |
P151835
|
FINISHED |
| Object | political propaganda |
—
|
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: political propaganda | Statement: [Korean Union of Musicians, usesMusicFor, political propaganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesMusicFor Context triple: [Korean Union of Musicians, usesMusicFor, political propaganda]
-
A.
musicUsed
Indicates that one entity makes use of or incorporates another entity as music, such as in a performance, production, or media context.
-
B.
usesMusicEnsemble
Indicates that one entity employs or incorporates a particular music ensemble in carrying out an action, function, or production.
-
C.
usesMusicVideo
Indicates that one entity incorporates or features another entity as a music video.
-
D.
usesTuneOf
Indicates that one work is created to be performed with, or is based on, the melody or musical setting originally belonging to another work.
-
E.
usesMusicalElement
Indicates that one entity employs or incorporates a particular musical element (such as rhythm, melody, harmony, or timbre) in its composition, performance, or structure.
- F. None of above. chosen
Provenance (4 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1977ee5d08190a9519d7867d6bef9 |
completed | April 29, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
| PDg | Predicate description generation | batch_69f01d88b4ec8190a2a17a88e0eda178 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 17, 2026, 5:06 p.m.