Triple
T18417001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonio Dixon |
E441918
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Love on Top |
—
|
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: Love on Top | Statement: [Antonio Dixon, notableWork, Love on Top]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Love on Top Context triple: [Antonio Dixon, notableWork, Love on Top]
-
A.
Love on Top
chosen
"Love on Top" is an upbeat R&B song by Beyoncé, celebrated for its key changes, retro-inspired sound, and powerful vocal performance.
-
B.
On Top of You
"On Top of You" is a song by the American punk rock band Insomniac.
-
C.
Girls on Top
Girls on Top is a mid-1980s British sitcom featuring Tracey Ullman as part of an all-female ensemble cast living together in a London flat.
-
D.
Girls on Top
Girls on Top is the alias of British music producer and songwriter Richard X, under which he released influential bootleg and mashup tracks in the early 2000s.
-
E.
On Top
"On Top" is a 1966 studio album by Motown vocal group the Four Tops, showcasing their soulful harmonies and classic Detroit sound.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a284b608190b77c360a72aceb7a |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 10:47 a.m.