Triple
T23598033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UEFA Cup 1997–98 with Inter Milan |
E582671
|
entity |
| Predicate | previousUEFACupTitlesForInter |
P140455
|
FINISHED |
| Object | 1990–91 |
—
|
LITERAL 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: 1990–91 | Statement: [UEFA Cup 1997–98 with Inter Milan, previousUEFACupTitlesForInter, 1990–91]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousUEFACupTitlesForInter Context triple: [UEFA Cup 1997–98 with Inter Milan, previousUEFACupTitlesForInter, 1990–91]
-
A.
UEFAInterCitiesFairsCupTitles
Indicates the number of UEFA Inter-Cities Fairs Cup titles an entity has won.
-
B.
numberOfUEFACupTitles
chosen
Indicates the number of UEFA Cup titles that an entity has won.
-
C.
UEFAEuropaLeagueTitles
Indicates the number of UEFA Europa League championship titles an entity has won.
-
D.
UEFACupWinnersCupTitleSeason
Indicates the specific football season in which a team won the UEFA Cup Winners' Cup title.
-
E.
UEFAChampionsLeagueTitles
Indicates the number of UEFA Champions League titles an entity (typically a football club) has won.
- F. None of above.
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_69e248f9e0a08190814772847003b1ff |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b091992c819085f8aa6cb91cb76a |
completed | April 29, 2026, 7:17 a.m. |
| PD | Predicate disambiguation | batch_69f118c96a0081908a8ac98ef7e7e60c |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:43 p.m.