Triple
T16027488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Russell |
E388753
|
entity |
| Predicate | genre of associated act |
P38924
|
FINISHED |
| Object | soft rock |
—
|
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: soft rock | Statement: [Graham Russell, genre of associated act, soft rock]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genre of associated act Context triple: [Graham Russell, genre of associated act, soft rock]
-
A.
genreAssociatedWith
chosen
Indicates a relationship where a work, item, or entity is linked to or categorized under a particular genre.
-
B.
associatedWithGenreElement
Indicates that something has a connection or linkage to a specific genre-related element (such as a motif, convention, or stylistic feature).
-
C.
legalGenre
Indicates that one entity is classified as a legal genre or category of law-related content for the other entity.
-
D.
associatedWithGenreScene
Indicates that an entity is connected or related to a particular genre scene, such as a specific stylistic or cultural subcommunity within a broader genre.
-
E.
genreOfJudgment
Indicates the specific legal category or type under which a particular judgment is classified.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1858a00888190b8505071575dc56f |
completed | April 17, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e1826a4f7c8190aba6d4f1075141b0 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:56 a.m.