Triple
T19532674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tameka "Tiny" Cottle |
E488692
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Tiny |
—
|
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: Tiny | Statement: [Tameka "Tiny" Cottle, nickname, Tiny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tiny Context triple: [Tameka "Tiny" Cottle, nickname, Tiny]
-
A.
Tiny
Tiny is the giant blue ox companion of the legendary lumberjack Paul Bunyan in American folklore.
-
B.
Tiny
Tiny was the ironic nickname of Bernard Freyberg, a highly decorated British-New Zealand military commander and World War II general.
-
C.
Tiny
Tiny was the ironic nickname of Edmund Ironside, the early 11th-century English king known for his strength and resistance against Danish invasion.
-
D.
Tiny
Tiny is the nickname of Nate Archibald, a Hall of Fame NBA point guard renowned for leading the league in both scoring and assists in the same season.
-
E.
Tiny
chosen
Tiny is the stage name of Tameka "Tiny" Cottle, an American singer-songwriter and television personality best known as a member of the R&B group Xscape and for her appearances on reality TV.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6364091f4819088b27d0ffdf6010d |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.