Triple
T13624677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thom Bell |
E325546
|
entity |
| Predicate | wroteSong |
P2831
|
FINISHED |
| Object | Break Up to Make Up |
E325543
|
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: Break Up to Make Up | Statement: [Thom Bell, wroteSong, Break Up to Make Up]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Break Up to Make Up Context triple: [Thom Bell, wroteSong, Break Up to Make Up]
-
A.
Break Up to Make Up
chosen
"Break Up to Make Up" is a classic soul ballad, best known as a hit song by The Stylistics co-written by Linda Creed.
-
B.
Break Up
"Break Up" is a collaborative studio album by Scarlett Johansson and Pete Yorn that blends indie pop and folk influences in a concept inspired by Serge Gainsbourg and Brigitte Bardot’s duets.
-
C.
Break Up
"Break Up" is a song by American R&B singer Mario, best known for its smooth production and themes of romantic conflict and separation.
-
D.
The Break-Up
The Break-Up is a 2006 romantic comedy-drama film starring Jennifer Aniston and Vince Vaughn as a couple navigating a messy split while still sharing their condo.
-
E.
Kiss and Make Up
"Kiss and Make Up" is a song featured on the album "Under the Blue Moon."
- 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_69d8076aae28819092cf636190ee5529 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbe9b0b648190afee93121483f45f |
completed | April 12, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f77fa4c5fc8190bd791f181fce2aa1 |
completed | May 3, 2026, 5:02 p.m. |
Created at: April 9, 2026, 9:50 p.m.