Triple
T12159826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Contrapunctus X |
E289673
|
entity |
| Predicate | isRecordedOn |
P47967
|
FINISHED |
| Object | numerous classical recordings |
—
|
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: numerous classical recordings | Statement: [Contrapunctus X, isRecordedOn, numerous classical recordings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRecordedOn Context triple: [Contrapunctus X, isRecordedOn, numerous classical recordings]
-
A.
reRecordedFrom
Indicates that one recording is a new recording derived from, based on, or made again from an earlier recording.
-
B.
recordedFor
Indicates that something has been documented, captured, or logged on behalf of or in association with a particular entity or context.
-
C.
recordingOf
chosen
Indicates that one entity is an audio or video capture or performance that documents, represents, or preserves another entity (such as a work, event, or expression).
-
D.
recorded
Indicates that one entity captured, stored, or documented information, audio, video, or data about another entity or event.
-
E.
mayBeRecordedAs
Indicates that something can optionally be documented or stored in a recorded form, but is not required to be.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915d7109481908bf5fe512bba3c89 |
completed | April 10, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69d9150c18148190bf8152189c0e5fca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:50 p.m.