Triple
T37616616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | amadinda xylophone |
E935940
|
entity |
| Predicate | malletType |
P148192
|
FINISHED |
| Object | wooden beaters |
—
|
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: wooden beaters | Statement: [amadinda xylophone, malletType, wooden beaters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: malletType Context triple: [amadinda xylophone, malletType, wooden beaters]
-
A.
batType
Indicates the specific category or kind of bat that an entity belongs to.
-
B.
hammerType
chosen
Indicates the specific kind or category of hammer associated with an entity.
-
C.
muzzleType
Indicates the specific style or configuration of a muzzle associated with an entity, such as a weapon or animal.
-
D.
typeOfHitter
Indicates the specific hitting style or category that characterizes a hitter in a given context.
-
E.
MAMAType
Indicates a classification relationship where an entity is assigned a specific type or category within the MAMA schema or framework.
- 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_69f76ed16b748190ad6add183b1be688 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.