Triple
T28698475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Rasmussen |
E729479
|
entity |
| Predicate | disciplineChange |
P165232
|
FINISHED |
| Object | from mountain biking to road cycling |
—
|
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: from mountain biking to road cycling | Statement: [Michael Rasmussen, disciplineChange, from mountain biking to road cycling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disciplineChange Context triple: [Michael Rasmussen, disciplineChange, from mountain biking to road cycling]
-
A.
disciplineRenamedTo
Indicates that an existing discipline has had its name changed to a new specified name.
-
B.
currentDiscipline
Indicates the disciplinary field or area of study in which an entity is presently engaged or classified.
-
C.
disciplineCode
Indicates the specific field, subject area, or branch of study/classification to which an entity is assigned or categorized.
-
D.
regulatesDiscipline
Indicates that one entity establishes or enforces rules, standards, or controls governing the conduct or discipline of another entity.
-
E.
disciplineIssues
Indicates that one entity has recorded or is associated with disciplinary problems, violations, or behavior issues involving another entity.
- F. None of above. chosen
Provenance (4 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_69f043e6e9688190b6bdd6e5665498ff |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 28, 2026, 5:41 a.m.