Triple
T1120929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fallin' |
E24608
|
entity |
| Predicate | performer |
P1363
|
FINISHED |
| Object | Alicia Keys |
E2161
|
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: Alicia Keys | Statement: [Fallin', performer, Alicia Keys]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alicia Keys Context triple: [Fallin', performer, Alicia Keys]
-
A.
Alicia Keys
chosen
Alicia Keys is a Grammy-winning American singer, songwriter, and pianist known for soulful R&B hits like "Fallin'" and "No One."
-
B.
Jill Scott
Jill Scott is an American singer-songwriter, poet, and actress known for her soulful neo-soul music and powerful, expressive vocals.
-
C.
Lauryn Hill
Lauryn Hill is an American singer, rapper, songwriter, and producer renowned for her groundbreaking work with the Fugees and her influential solo album "The Miseducation of Lauryn Hill."
-
D.
Mary J. Blige
Mary J. Blige is an American singer, songwriter, and actress widely known as the "Queen of Hip-Hop Soul" for her influential blend of R&B, soul, and hip-hop.
-
E.
Keyshia Cole
Keyshia Cole is an American R&B singer, songwriter, and television personality known for her soulful vocals and hit albums in the 2000s.
- 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_69a4940712c88190aa244f3fc6070a65 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bbbe58588190a5ef6346e269d5f3 |
completed | March 1, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac59a221888190a3ffdb713e7cd143 |
completed | March 7, 2026, 5 p.m. |
Created at: March 1, 2026, 7:43 p.m.