Triple
T5351714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | She Loves You |
E102592
|
entity |
| Predicate | famousRefrain |
P32220
|
FINISHED |
| Object | yeah, yeah, yeah |
—
|
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: yeah, yeah, yeah | Statement: [She Loves You, famousRefrain, yeah, yeah, yeah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: famousRefrain Context triple: [She Loves You, famousRefrain, yeah, yeah, yeah]
-
A.
refrain
Indicates that an entity deliberately holds back from performing a particular action or behavior.
-
B.
refrainWord
Indicates that one entity avoids using, mentioning, or expressing a particular word or term in relation to another entity or context.
-
C.
refrainTranslation
Indicates that one expression is a translation of the repeated or recurring part (refrain) of another expression, typically in a different language.
-
D.
refrainText
chosen
Indicates that a piece of text functions as the recurring refrain or repeated line within a larger work, such as a song or poem.
-
E.
commonlySungStanzas
Indicates that certain stanzas of a song or poem are those most frequently sung or performed in practice.
- 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_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd861188ac81908ef2b1f25cc6c864 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.