Triple
T9981351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wolves |
E196457
|
entity |
| Predicate | notablePlayer |
P304
|
FINISHED |
| Object | Sam Cassell |
E325523
|
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: Sam Cassell | Statement: [Wolves, notablePlayer, Sam Cassell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Cassell Context triple: [Wolves, notablePlayer, Sam Cassell]
-
A.
Sam Cassell
chosen
Sam Cassell is a former NBA point guard and three-time champion known for his clutch play and later work as an assistant coach.
-
B.
Lee Cullen
Lee Cullen is a key protagonist in the 1996 action film "Eraser," portrayed as a whistleblower under federal protection whose testimony exposes a major arms-dealing conspiracy.
-
C.
John Cassisi
John Cassisi is an American former child actor best known for playing the mob boss Fat Sam in the 1976 musical gangster film "Bugsy Malone."
-
D.
Chris Allison
Chris Allison is a music producer known for his work on Coldplay’s debut album "Parachutes."
-
E.
Alex Ligertwood
Alex Ligertwood is a Scottish singer best known as a longtime lead vocalist for the rock band Santana.
- 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_69ca82efbce081908179b4b9c65096eb |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb8bb3dc481909c65c37303e44037 |
completed | April 2, 2026, 12:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d257e888908190a7187e26ba025a44 |
completed | April 5, 2026, 12:39 p.m. |
Created at: March 30, 2026, 8:49 p.m.