Triple
T9051173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ca trù |
E216885
|
entity |
| Predicate | typicalPerformerRole |
P18942
|
FINISHED |
| Object | female singer (đào nương) |
—
|
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: female singer (đào nương) | Statement: [Ca trù, typicalPerformerRole, female singer (đào nương)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPerformerRole Context triple: [Ca trù, typicalPerformerRole, female singer (đào nương)]
-
A.
typicalPerformerRoleType
Indicates the usual or characteristic role type that a performer commonly plays or is associated with in their performances.
-
B.
typicalRole
chosen
Indicates that one entity serves as the usual, characteristic, or commonly expected role or function of another entity.
-
C.
musicalRole
Indicates the specific function or part an entity performs within a musical context, such as in a performance, composition, or ensemble.
-
D.
performerType
Indicates the role or category of performer responsible for carrying out an action or participating in an event.
-
E.
talentShowRole
Indicates the specific function or position an entity holds within the context of a talent show (e.g., performer, judge, host).
- 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_69ca83d362e88190ae44b4e4dc194209 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b54423081908d9fd985109e336a |
completed | April 1, 2026, 12:48 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee566b081909e3cdaf551dbd0ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:10 p.m.