Triple
T38561487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1996 UEFA Champions League Final |
E928085
|
entity |
| Predicate | AjaxGoalkeeper |
P34552
|
FINISHED |
| Object | Edwin van der Sar |
—
|
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: Edwin van der Sar | Statement: [1996 UEFA Champions League Final, AjaxGoalkeeper, Edwin van der Sar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AjaxGoalkeeper Context triple: [1996 UEFA Champions League Final, AjaxGoalkeeper, Edwin van der Sar]
-
A.
MexicoGoalkeeper
Indicates that an entity serves as a goalkeeper for a Mexican national or club soccer team.
-
B.
goalkeeperArgentina
Indicates that the subject is the goalkeeper for a team representing Argentina.
-
C.
arsenalGoalkeeper
Indicates that the person serves as a goalkeeper for the Arsenal football team.
-
D.
goaltender
chosen
Indicates a relationship where an entity serves as the goalkeeper or primary defender of the goal for a team in a game or sport.
-
E.
goalkeeperAction
Indicates actions performed by a goalkeeper in the context of defending the goal, such as saving, catching, blocking, or distributing the ball.
- 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_69f76eb8d1808190a588af29d8b266d6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.