Triple
T20457355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coconut Records |
E501826
|
entity |
| Predicate | hasSong |
P20452
|
FINISHED |
| Object |
Back to You
"Back to You" is an indie pop song by Coconut Records, the solo music project of actor and musician Jason Schwartzman.
|
E1433197
|
NE FINISHED |
How this triple was built (4 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: Back to You | Statement: [Coconut Records, hasSong, Back to You]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Back to You Context triple: [Coconut Records, hasSong, Back to You]
-
A.
Back to You
"Back to You" is an American sitcom that aired in the late 2000s, starring Kelsey Grammer and Patricia Heaton as reunited local news anchors.
-
B.
Back to You
"Back to You" is a song by American singer-songwriter John Mayer from his debut studio album "Room for Squares."
-
C.
Back to You
"Back to You" is a pop single by British singer and former The Saturdays member Mollie King, marking one of her early solo releases.
-
D.
Coming Back to You
"Coming Back to You" is a reflective, melancholic song by Leonard Cohen from his 1984 album Various Positions, noted for its poetic lyrics and understated arrangement.
-
E.
Running Back to You
"Running Back to You" is a gospel/R&B song featured on the album *I Need an Angel* by Ruben Studdard.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Back to You Triple: [Coconut Records, hasSong, Back to You]
Generated description
"Back to You" is an indie pop song by Coconut Records, the solo music project of actor and musician Jason Schwartzman.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Back to You Target entity description: "Back to You" is an indie pop song by Coconut Records, the solo music project of actor and musician Jason Schwartzman.
-
A.
Back to You
"Back to You" is an American sitcom that aired in the late 2000s, starring Kelsey Grammer and Patricia Heaton as reunited local news anchors.
-
B.
Back to You
"Back to You" is a song by American singer-songwriter John Mayer from his debut studio album "Room for Squares."
-
C.
Back to You
"Back to You" is a pop single by British singer and former The Saturdays member Mollie King, marking one of her early solo releases.
-
D.
Coming Back to You
"Coming Back to You" is a reflective, melancholic song by Leonard Cohen from his 1984 album Various Positions, noted for its poetic lyrics and understated arrangement.
-
E.
Running Back to You
"Running Back to You" is a gospel/R&B song featured on the album *I Need an Angel* by Ruben Studdard.
- F. None of above. chosen
Provenance (5 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e696a2a8a88190992211b09295d8ea |
completed | April 20, 2026, 9:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a088b10b6608190a88f466dccf31322 |
completed | May 16, 2026, 3:19 p.m. |
| NEDg | Description generation | batch_6a088c75b09081908a35bc7a9b6a45ce |
completed | May 16, 2026, 3:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a088d8c3ab08190a399dba52e3c99f5 |
completed | May 16, 2026, 3:30 p.m. |
Created at: April 16, 2026, 11:33 a.m.