Triple
T268872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Refuge (When It’s Cold Outside) |
E5581
|
entity |
| Predicate | hasArtistRole |
P9640
|
FINISHED |
| Object | John Legend – lead vocals |
—
|
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: John Legend – lead vocals | Statement: [Refuge (When It’s Cold Outside), hasArtistRole, John Legend – lead vocals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArtistRole Context triple: [Refuge (When It’s Cold Outside), hasArtistRole, John Legend – lead vocals]
-
A.
hasArtist
Indicates that an entity (such as a work or item) is associated with or created by a specific artist.
-
B.
primaryArtist
Indicates that an entity is the main or lead artist responsible for a creative work, as opposed to supporting or contributing artists.
-
C.
notableArtistInCollection
Indicates that an artist is prominently represented or recognized within a particular collection.
-
D.
hasArranger
Indicates that one entity serves as the arranger (e.g., musically or structurally) for another entity, such as a work, performance, or composition.
-
E.
notableArtist
Indicates that the subject is an artist who is widely recognized or distinguished for their work.
- F. None of above. chosen
Provenance (4 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_69a25853594c8190b05ec3a586ec88bf |
completed | Feb. 28, 2026, 2:52 a.m. |
| NER | Named-entity recognition | batch_69a25dae4a0c8190a66cf6ed3889851c |
completed | Feb. 28, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69a25b70d99c819085d8381a313a2a34 |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25d6ec9688190b2ba027756b57d25 |
completed | Feb. 28, 2026, 3:13 a.m. |
Created at: Feb. 28, 2026, 2:57 a.m.