Triple
T14969843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teaira McCowan |
E373286
|
entity |
| Predicate | draftedBy |
P2210
|
FINISHED |
| Object | Indiana Fever |
E137059
|
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: Indiana Fever | Statement: [Teaira McCowan, draftedBy, Indiana Fever]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Indiana Fever Context triple: [Teaira McCowan, draftedBy, Indiana Fever]
-
A.
Indiana Fever
chosen
The Indiana Fever are a professional women's basketball team based in Indianapolis that competes in the WNBA.
-
B.
Fort Wayne Mad Ants
The Fort Wayne Mad Ants are a professional basketball team in the NBA G League based in Fort Wayne, Indiana.
-
C.
NOLA Gold
NOLA Gold is a professional rugby union team based in New Orleans, Louisiana, competing in Major League Rugby in the United States.
-
D.
New Jersey Wildcats
The New Jersey Wildcats are a former American women’s soccer club that competed in the USL W-League and helped develop several future U.S. national team players.
-
E.
Kansas City Wiz
Kansas City Wiz was the original name of the Major League Soccer club now known as Sporting Kansas City.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6e59a7c8190a1634a706ea68fda |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9692e4fc8190a1194a41fc8a832c |
completed | May 9, 2026, 2:06 a.m. |
Created at: April 10, 2026, 2:49 a.m.