Triple
T14045657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ceremonials |
E337948
|
entity |
| Predicate | track |
P17929
|
FINISHED |
| Object | Lover to Lover |
E1076603
|
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: Lover to Lover | Statement: [Ceremonials, track, Lover to Lover]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lover to Lover Context triple: [Ceremonials, track, Lover to Lover]
-
A.
Lover to Lover
chosen
"Lover to Lover" is a song by English indie rock band Florence + The Machine from their second studio album, Ceremonials.
-
B.
The Lover in Me
The Lover in Me is a 1988 pop and dance-oriented studio album by Scottish singer Sheena Easton that marked a successful shift toward a more contemporary, R&B-influenced sound.
-
C.
Lover Alot
Lover Alot is a hard-rock track by Aerosmith featured on their 2012 studio album "Music from Another Dimension!".
-
D.
Your Lover
"Your Lover" is a song featured on the album "Something About Faith" by American R&B singer Faith Evans.
-
E.
Lovergirl
"Lovergirl" is a popular 1984 R&B and funk single by American singer Teena Marie, known for its catchy groove and powerful vocals.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de312df37081909f45ce3e219af5dc |
completed | April 14, 2026, 12:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd099b7788190a7c309dba450e58f |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:20 p.m.