Triple
T23906379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London After Midnight |
E601207
|
entity |
| Predicate | musicForReconstructionBy |
P69477
|
FINISHED |
| Object | Robert Israel |
—
|
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: Robert Israel | Statement: [London After Midnight, musicForReconstructionBy, Robert Israel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: musicForReconstructionBy Context triple: [London After Midnight, musicForReconstructionBy, Robert Israel]
-
A.
musicMotif
Indicates a recurring musical idea, theme, or pattern that appears multiple times within a composition or across related works.
-
B.
musicUsed
chosen
Indicates that one entity makes use of or incorporates another entity as music, such as in a performance, production, or media context.
-
C.
musicBy
Indicates that a piece of music, performance, or recording is created, composed, or performed by a specified musical artist or group.
-
D.
musicElement
Indicates a relationship where something functions as a component or structural unit within a piece of music or musical composition.
-
E.
musicFusionOf
Indicates a relationship where one musical work, style, or element is created by combining or blending two or more distinct musical sources or genres.
- 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_69e295364a488190bcac702e9bb7f764 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce91144c8190b894e25a45dfd7c9 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:35 p.m.