Triple
T4366021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D'Lila Star Combs |
E98773
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Chance Combs |
E424211
|
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: Chance Combs | Statement: [D'Lila Star Combs, sibling, Chance Combs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chance Combs Context triple: [D'Lila Star Combs, sibling, Chance Combs]
-
A.
Chance Combs
chosen
Chance Combs is the daughter of rapper and entrepreneur Sean "Diddy" Combs and model Sarah Chapman.
-
B.
Justin Dior Combs
Justin Dior Combs is an American socialite, former college football player, and media personality best known as the son of hip-hop mogul Sean "Diddy" Combs.
-
C.
King Combs
King Combs is an American rapper, singer, and model, best known as the son of Sean "Diddy" Combs and for his nostalgic, 1990s-inspired hip-hop and R&B music.
-
D.
Bryson Tiller
Bryson Tiller is an American singer, rapper, and songwriter known for pioneering the modern trap-soul sound with hits like "Don't" and "Exchange."
-
E.
Don Toliver
Don Toliver is an American rapper and singer known for his melodic trap style and collaborations with major artists like Travis Scott and Kanye West.
- 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_69b3454c772081908e20173e379e8ebe |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35200263081909bb326a4d7a8db99 |
completed | March 12, 2026, 11:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5f5d4612c8190ac5163d50299f8ab |
completed | March 14, 2026, 11:57 p.m. |
Created at: March 12, 2026, 11:17 p.m.