st: stset: I can't get rid of a probable error

[Martin Neugebauer <martin_neugebauer@zuma-mannheim.de>]

Hopefully somebody can help me out with this:

I am trying to estimate the average marriage time until divorce. When I 
run the stset command, I always get the following "probable error":

id:  respid
     failure event:  failed == 1
obs. time interval:  (date0, date1]
 exit on or before:  failure
    t for analysis:  (time-origin)
            origin:  time date0
                if:  partnr==minpart

------------------------------------------------------------------------------
     7277  total obs.
       10  overlapping records (date1[_n-1]>date0)  PROBABLE ERROR
      468  ignored per request (if(), etc.)
------------------------------------------------------------------------------
     6799  obs. remaining, representing
     6799  subjects
     1067  failures in single failure-per-subject data
 116093.5  total analysis time at risk, at risk from t =         0
                             earliest observed entry t =         0
                                  last observed exit t =        49

What does Stata mean by "overlapping records (date1[_n-1]>date0)"? How 
can I solve the probable error?

(do-file):

gen failed=1
replace failed=0 if  JScheidung==.
replace failed=9 if   JSterbe <=2000
gen date0= J_Heirat
gen date1= JScheidung
replace date1= 2000 if JScheidung==.
replace date1= JSterbe if JSterbe<=2000
drop if date0==.
drop if date1==.
replace date1=date1+ .5 if date1==date0
sort respid partnr
by respid (partnr):  gen minpart=partnr[1]
stset date1, id(respid) time0(date0) origin (time date0) failure 
(failed==1) if(partnr==minpart)

Thank you!
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/