Full text indexes for entity extraction

Hi,

I'm trying to do entity extraction from tweets on SAP Hana One. I've set up a table where I put the tweet texts (schema below) and I've followed the instructions in http://scn.sap.com/community/developer-center/hana/blog/2013/01/03/sap-hana-text-analysis but the $TA table is empty. Most of the tweets are English, some aren't, but I expect to see at least something.

I also tried the sentiment analysis example in http://scn.sap.com/community/developer-center/hana/blog/2013/06/19/real-time-sentiment-rating-of-movies-on-sap-hana-one but again - the $TA table is empty.

I tried do create the full text indexes both with the SYSTEM user and another user I created with fairly high permissions.

What am I doing wrong?

CREATE COLUMN TABLE TWEETS3 (ID NVARCHAR(500), TXT NVARCHAR(5000), PRIMARY KEY(ID))

Create FullText Index "TWT_FTI" On "TWEETS3"("TXT")

TEXT ANALYSIS ON

CONFIGURATION 'EXTRACTION_CORE';

--the table TWEETS3 contains 20,000 rows but the following query returns 0 rows:

SELECT * FROM "$TA_TWT_FTI"

Thanks!