Triple
T31945673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | H 81 |
E815644
|
entity |
| Predicate | referredWorkFirstPublicationForm |
P14177
|
FINISHED |
| Object | voice and piano |
—
|
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: voice and piano | Statement: [H 81, referredWorkFirstPublicationForm, voice and piano]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referredWorkFirstPublicationForm Context triple: [H 81, referredWorkFirstPublicationForm, voice and piano]
-
A.
notableWorkPublicationForm
Indicates the medium or format in which a notable work was originally published or made publicly available.
-
B.
initialPublicationForm
chosen
Indicates the original format or medium in which a work was first published.
-
C.
firstPublicationOfContainingWork
Indicates that the related entity is the earliest published work in which the referenced work or content first appeared.
-
D.
workFirstPublicationApproximate
Indicates that the date of a work’s first publication is not exact but an approximate or estimated value.
-
E.
formerPublication
Indicates that an entity was previously published in, or associated as a publication with, another entity but is no longer currently so.
- 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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: May 1, 2026, 12:06 a.m.