Triple
T14853969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tommy Vercetti |
E349301
|
entity |
| Predicate | ally |
P4662
|
FINISHED |
| Object | Ken Rosenberg |
—
|
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: Ken Rosenberg | Statement: [Tommy Vercetti, ally, Ken Rosenberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ken Rosenberg Context triple: [Tommy Vercetti, ally, Ken Rosenberg]
-
A.
Ken Rosenberg
chosen
Ken Rosenberg is a neurotic, fast-talking criminal lawyer and associate of the protagonist in the Grand Theft Auto series, most prominently featured in Vice City.
-
B.
William Rosenberg
William Rosenberg was an American entrepreneur best known for creating the coffee and doughnut chain that became Dunkin' Donuts.
-
C.
Michael Rosenberg
Michael Rosenberg is a television producer and executive known for his work on the Western drama series "Hell on Wheels."
-
D.
Dave Rosenberg
Dave Rosenberg is a technology entrepreneur best known as a co-founder of MuleSoft, a leading integration and API management platform company.
-
E.
Mark Rosenthal
Mark Rosenthal is an American screenwriter known for co-writing major Hollywood films, including contributing to the story for "Star Trek VI: The Undiscovered Country."
- 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_69d822ed7e1881909b90fca143ad7e34 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded44318f0819080b6c599f2d3474f |
completed | April 14, 2026, 11:56 p.m. |
Created at: April 10, 2026, 1:54 a.m.