Triple
T5105057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rod Thorn |
E115071
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Rod Thorn |
E115071
|
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: Rod Thorn | Statement: [Rod Thorn, name, Rod Thorn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rod Thorn Context triple: [Rod Thorn, name, Rod Thorn]
-
A.
Rod Thorn
chosen
Rod Thorn is an American former NBA player, coach, and longtime league executive best known for his front-office roles with the Chicago Bulls and New Jersey Nets.
-
B.
Roy Tarpley
Roy Tarpley was an American professional basketball player, best known as a talented but troubled Dallas Mavericks big man whose NBA career was derailed by substance abuse issues.
-
C.
Paul Westphal
Paul Westphal was an American Hall of Fame basketball player and coach best known as an All-Star guard for the Phoenix Suns in the 1970s.
-
D.
Gene Bartow
Gene Bartow was a highly respected American college basketball coach best known for building the UAB program from scratch and for succeeding John Wooden at UCLA.
-
E.
Art Riley
Art Riley was a background artist known for his work on classic animated films and shorts, including projects for major American studios in the mid-20th century.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7589e40c8190a46e4a1b7142be14 |
completed | March 20, 2026, 4:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beba95dbd48190a7d87f3af77424e0 |
completed | March 21, 2026, 3:34 p.m. |
Created at: March 20, 2026, 1:41 p.m.