Triple
T29721992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fire (L’enfant et les sortilèges) |
E752077
|
entity |
| Predicate | setToLibrettoBy |
P59320
|
FINISHED |
| Object | Colette |
—
|
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: Colette | Statement: [Fire (L’enfant et les sortilèges), setToLibrettoBy, Colette]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setToLibrettoBy Context triple: [Fire (L’enfant et les sortilèges), setToLibrettoBy, Colette]
-
A.
librettoBy
chosen
Indicates that a work’s libretto (the text of an opera or similar vocal work) was written by a particular person.
-
B.
includesLibretto
Indicates that one entity (typically a musical or operatic work or publication) contains or is accompanied by the full text/libretto of another work.
-
C.
sharesLibrettoWith
Indicates that two musical or theatrical works use the same libretto text.
-
D.
setToMusicIn
Indicates that something (typically text or lyrics) has been arranged or adapted to be performed as music within a particular work or context.
-
E.
setToMusicAs
Indicates that one entity (typically a text or work) has been adapted and arranged by another entity into a musical composition.
- 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_69f0d628c00c8190ab5ee7e423d7ec3c |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f672fbd174819094642a594a447e47 |
completed | May 2, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:37 p.m.