Triple
T25607088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verena Bentele |
E641941
|
entity |
| Predicate | paralympicMedalistIn |
P44415
|
FINISHED |
| Object | cross-country skiing |
—
|
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: cross-country skiing | Statement: [Verena Bentele, paralympicMedalistIn, cross-country skiing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paralympicMedalistIn Context triple: [Verena Bentele, paralympicMedalistIn, cross-country skiing]
-
A.
hasWonParalympicMedal
chosen
Indicates that an entity has earned at least one medal in a Paralympic Games competition.
-
B.
hasParalympicStatus
Indicates that an entity holds an official classification or recognition related to participation in the Paralympic Games or Paralympic movement.
-
C.
paralympicCounterpartOf
Indicates that one entity is the corresponding Paralympic version or equivalent of another entity, typically an Olympic event, sport, or competition.
-
D.
olympicChampionIn
Indicates that an entity has won a championship title in a specified Olympic sport or event.
-
E.
worldMedalist
Indicates that an entity has won a medal at a recognized world-level championship or world competition.
- 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_69e75dc6ccf081908d49578fd36a76d5 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f9e00c9c81909d2372a9ebc8a51f |
completed | May 2, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 4:39 p.m.