What if we extended this idea beyond one dataset to all discrete news events and entities: people, organizations, places.
Just like here you could get a timeline of key events, a graph of connected entities, links to original documents.
Newsrooms might already do this internally idk.
This code might work as a foundation. I love that it's RDF.
Oh Cthulhu, this is like a periscope into a septic tank...
"Brad Edwards" and "Bradley Edwards" might be the same individual.
Why are they all moving, what does the time axis represent?
I’m curious which LLM tools actually handled all 23k emails well.
This is the best rendition I've seen so far.
The Bill Clinton entity is interesting.
> 2009: Bill Clinton discontinued association with Jeffrey Epstein
> 2010: Jeffrey Epstein provided flights on jets to Bill Clinton
> 2010-2011: Jeffrey Epstein traveled via private aircraft with Bill Clinton
> 2011: Ghislaine Maxwell piloted helicopter for Bill Clinton
> 2014: Bill Clinton alleged presence at sex parties
> 2015: Bill Clinton distanced relationship from Jeffrey Epstein
Wasn't very good at discontinuing the relationship it seems.
Guess there is precedent for him lying about sexual activities though.
I think a sentiment analysis between the friendliness and social meetups between Epstein and other individuals would be useful.
Who were his friends after 2008 when he was first convicted?
Those who were still friends with him after 2008 were in on it or guilty by association, if not legally, socially.
Friends like Reid Hoffman and Larry Summers...
> From: Reid Hoffman
> Sent: 7/6/2015 5:04:31 PM
> To: jeffrey E. [[email protected]]
> Subject: RE: ICYMI
> slow progress.
> planning to see you in August.
> Hope you're well.
Larry Summers has too many to list. Doesn't look good though digging through them.
After seen this I interested in a map of each person to assist with knowing who they are, who they worked for during the email date, and who they currently work for.