Triple
T15766722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Jones |
E382238
|
entity |
| Predicate | notableSingle |
P3283
|
FINISHED |
| Object | Back Then |
E1175597
|
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: Back Then | Statement: [Mike Jones, notableSingle, Back Then]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Back Then Context triple: [Mike Jones, notableSingle, Back Then]
-
A.
Back Then
chosen
"Back Then" is a 2005 Southern hip hop single by American rapper Mike Jones that became his breakout hit and one of his most recognizable songs.
-
B.
Now & Then
Now & Then is a 1973 concept album by the Carpenters that blends their signature soft pop sound with a nostalgic medley of 1960s hits framed as a radio broadcast.
-
C.
See Now Then
See Now Then is a 2013 novel by Jamaica Kincaid that explores time, memory, and the unraveling of a marriage in a small New England town through a lyrical, experimental narrative style.
-
D.
Back When
"Back When" is a hit Afrobeat single by Nigerian artist Davido featuring Naeto C, known for helping launch Davido’s mainstream music career.
-
E.
Then and Now
Then and Now is a track featured on the album "Made in Brooklyn" by the American hip-hop group M.O.P.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e050b8154881908afe5191e6424f15 |
completed | April 16, 2026, 3 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff9099335c8190b6f0fb336b3dc212 |
completed | May 9, 2026, 7:52 p.m. |
Created at: April 10, 2026, 4:47 a.m.