Triple
T14757562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA 2K League 2020 season |
E346768
|
entity |
| Predicate | topScorer |
P6605
|
FINISHED |
| Object | Reezy |
E1118479
|
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: Reezy | Statement: [NBA 2K League 2020 season, topScorer, Reezy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Reezy Context triple: [NBA 2K League 2020 season, topScorer, Reezy]
-
A.
Reezy
chosen
Reezy is a professional NBA 2K League player best known for winning the league’s Most Valuable Player award in the 2020 season.
-
B.
Rockey
Rockey is the surname of Keller E. Rockey, a notable United States Marine Corps general who served during World War II.
-
C.
Rebbie
Rebbie is an American singer and the eldest child of the Jackson family, known for her R&B music career and songs like "Centipede."
-
D.
Zeebo
Zeebo was a Brazil-focused, low-cost 3G-enabled video game console designed to bring digital gaming to emerging markets.
-
E.
Reesing
Reesing is the surname of Todd Reesing, an American former college football quarterback best known for his record-setting career at the University of Kansas.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7ef0fd48190bd4a8af128ef274c |
completed | April 14, 2026, 11:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe24afff788190ab4925ead7ce90d2 |
completed | May 8, 2026, 6 p.m. |
Created at: April 10, 2026, 1:30 a.m.