Triple
T18270865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love Changes |
E437607
|
entity |
| Predicate | featuredArtist |
P997
|
FINISHED |
| Object | Meli'sa Morgan |
—
|
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: Meli'sa Morgan | Statement: [Love Changes, featuredArtist, Meli'sa Morgan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Meli'sa Morgan Context triple: [Love Changes, featuredArtist, Meli'sa Morgan]
-
A.
Meli'sa Morgan
chosen
Meli'sa Morgan is an American R&B and soul singer best known for her powerful vocals and hit songs in the 1980s.
-
B.
Nichole Millard
Nichole Millard is a screenwriter best known for co-writing the family sports comedy film "The Game Plan."
-
C.
Maren Larae Morris
Maren Larae Morris is an American country and pop singer-songwriter known for hits like "My Church" and "The Bones" and for blending country, pop, and R&B influences.
-
D.
Nichole Gilbert
Nichole Gilbert is a songwriter best known for co-writing the R&B song "If You Love Me."
-
E.
Mariel Sheets
Mariel Sheets is an American child actress best known for voicing Sally Brown in the animated feature film "The Peanuts Movie."
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ff7e00548190a28916a696831336 |
completed | April 19, 2026, 4:14 p.m. |
Created at: April 10, 2026, 10:34 a.m.