Triple
T30144844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murchunga |
E766226
|
entity |
| Predicate | vibrationSource |
P83120
|
FINISHED |
| Object | flexible metal tongue |
—
|
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: flexible metal tongue | Statement: [Murchunga, vibrationSource, flexible metal tongue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vibrationSource Context triple: [Murchunga, vibrationSource, flexible metal tongue]
-
A.
supportsVibration
Indicates that one entity provides the capability or functionality to handle, generate, or respond to vibration for another entity.
-
B.
hasHDVibration
Indicates that an entity provides or supports high-definition (precise, nuanced) vibration feedback in its interactions or operations.
-
C.
vibrationPattern
Indicates a specific recurring sequence or configuration of vibrations exhibited by or applied to an entity.
-
D.
hasCauseOfSound
Indicates that one entity is the source or origin of a particular sound produced or associated with another entity.
-
E.
noiseSource
chosen
Indicates that one entity is the origin or producer of a particular noise affecting another entity or the environment.
- 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_69f2247909048190ae86c2160cf8b566 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67e8b21048190b0fbccb10b2d3523 |
completed | May 2, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:18 p.m.