Triple
T31305006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Щелкунчик |
E798312
|
entity |
| Predicate | либреттист |
P134607
|
FINISHED |
| Object | Мариус Петипа |
—
|
NE NERFINISHED |
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: Мариус Петипа | Statement: [Щелкунчик, либреттист, Мариус Петипа]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: либреттист Context triple: [Щелкунчик, либреттист, Мариус Петипа]
-
A.
principalLibrettist
Indicates that one entity serves as the main librettist responsible for writing the text of a musical or operatic work for another entity.
-
B.
librettistOfParentWork
Indicates that one entity is the librettist who wrote the text (libretto) for the parent work associated with another entity.
-
C.
librettistOfOpera
chosen
Indicates that one entity is the librettist who wrote the text (libretto) for the specified opera.
-
D.
librettistNationality
Indicates the relationship between a librettist and the country or nationality with which they are associated.
-
E.
librettistOfWorkAppearingIn
Indicates that a person is the librettist responsible for the text of a work that appears within a larger composite work or collection.
- 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_69f224e0bd4c8190aab9b29a73f7aa3c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:14 p.m.