Triple
T35407353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teddy White |
E1023398
|
entity |
| Predicate | contributedRole |
P15464
|
FINISHED |
| Object | lyrics |
—
|
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: lyrics | Statement: [Teddy White, contributedRole, lyrics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contributedRole Context triple: [Teddy White, contributedRole, lyrics]
-
A.
collaboratorRole
Indicates the specific function, position, or capacity in which one collaborator participates in a shared activity or project with another.
-
B.
artifactRole
Indicates the specific function, purpose, or responsibility that an artifact has within a particular context or activity.
-
C.
compositionalRole
Indicates that one entity serves as a constituent or component within the structure, function, or meaning of another entity.
-
D.
notableWorkRole
chosen
Indicates that a person’s role or position is specifically associated with the creation, performance, or contribution to a notable work.
-
E.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another entity.
- 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_69f76df43ca4819098711ca4370f1bb9 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fed6da0390819096b88ef4714b144e |
completed | May 9, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69fed53517d081909966f31707625f1a |
completed | May 9, 2026, 6:33 a.m. |
Created at: May 3, 2026, 4:03 p.m.