Triple
T23180276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Playing for Keeps |
E579440
|
entity |
| Predicate | hasBside |
P15273
|
FINISHED |
| Object | Too Much |
—
|
NE NERFINISHED |
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: Too Much | Statement: [Playing for Keeps, hasBside, Too Much]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Too Much Context triple: [Playing for Keeps, hasBside, Too Much]
-
A.
Too Much
"Too Much" is a 1997 pop ballad by the Spice Girls that became one of their hit singles, showcasing their signature harmonies and topping charts in several countries.
-
B.
Too Much
chosen
"Too Much" is a reflective, emotionally charged song by Canadian rapper Drake that appears on his 2013 album *Nothing Was the Same*.
-
C.
Too Much
"Too Much" is a song by the American indie rock band Pollinator.
-
D.
Too Much
"Too Much" is a song by American musician Sufjan Stevens from his experimental, electronic-influenced album *The Age of Adz*.
-
E.
Too Much
"Too Much" is a 2023 pop-rap single by Australian artist The Kid LAROI, featuring Jung Kook and Central Cee, known for its catchy hook and themes of emotional excess in relationships.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f6ebff48190ad1543051ca0239b |
completed | April 29, 2026, 4:56 a.m. |
Created at: April 17, 2026, 4:04 p.m.