Triple
T14515587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1989 |
E340507
|
entity |
| Predicate | track |
P17929
|
FINISHED |
| Object | Shake It Off |
E227284
|
NE 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: Shake It Off | Statement: [1989, track, Shake It Off]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shake It Off Context triple: [1989, track, Shake It Off]
-
A.
Shake It Off
"Shake It Off" is an upbeat 2005 R&B-pop single by Mariah Carey from her album "The Emancipation of Mimi," known for its catchy hook about moving on from a bad relationship.
-
B.
Shake It Off
chosen
"Shake It Off" is a 2014 upbeat pop anthem by Taylor Swift known for its catchy hook and message about brushing off criticism.
-
C.
All About That Bass
"All About That Bass" is a 2014 doo-wop-influenced pop song by Meghan Trainor that became a global hit for its catchy hook and body-positivity message.
-
D.
Can't Stop the Feeling!
"Can't Stop the Feeling!" is a 2016 upbeat pop song by Justin Timberlake, known for its feel-good dance vibe and association with the animated film Trolls.
-
E.
Drunk in Love
"Drunk in Love" is a sultry, trap-influenced R&B song by Beyoncé featuring Jay-Z that became one of her signature hits following its release in 2013.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de9a6d82988190b6f957012bcc63d4 |
completed | April 14, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd8aaeaf40819087fa0db989813e02 |
completed | May 8, 2026, 7:03 a.m. |
Created at: April 10, 2026, 1:21 a.m.