Triple
T28768725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcel Hirscher |
E726348
|
entity |
| Predicate | specializesInDiscipline |
P140458
|
FINISHED |
| Object | slalom |
—
|
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: slalom | Statement: [Marcel Hirscher, specializesInDiscipline, slalom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specializesInDiscipline Context triple: [Marcel Hirscher, specializesInDiscipline, slalom]
-
A.
subjectSpecialization
chosen
Indicates that one subject focuses on, or has expertise in, a particular field, topic, or area of knowledge.
-
B.
disciplineOfRecord
Indicates the specific field, subject area, or branch of knowledge in which something is formally recorded or recognized.
-
C.
subDisciplineOf
Indicates that one discipline is a more specialized or narrower field within another, broader discipline.
-
D.
associatedWithDiscipline
Indicates that an entity has a relevant connection or involvement with a particular academic, professional, or thematic discipline.
-
E.
isConsideredSpecialtyOf
Indicates that one field, practice, or area of expertise is regarded as a specialized branch or subset of another broader field.
- 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_69f03198be14819098fa74e48b3749bf |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 28, 2026, 6:14 a.m.