Triple
T18353463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whiskey You’re the Devil |
E439727
|
entity |
| Predicate | hasRefrainMentioning |
P114550
|
FINISHED |
| Object | whiskey |
—
|
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: whiskey | Statement: [Whiskey You’re the Devil, hasRefrainMentioning, whiskey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRefrainMentioning Context triple: [Whiskey You’re the Devil, hasRefrainMentioning, whiskey]
-
A.
hasRefrainRelatedTo
Indicates that a refrain (repeated musical or textual section) in one work is thematically or content-wise related to another specified subject or element.
-
B.
hasLyricsMentioning
chosen
Indicates that the referenced lyrics explicitly mention or refer to the specified entity.
-
C.
refrain
Indicates that an entity deliberately holds back from performing a particular action or behavior.
-
D.
hasChorusIn
Indicates that a musical work includes a chorus section within the specified part or segment.
-
E.
refrainText
Indicates that a piece of text functions as the recurring refrain or repeated line within a larger work, such as a song or poem.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d37bc08190abc9b4e8c937c914 |
completed | April 19, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.