Triple
T6343063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Court of Arbitration for Sport |
E142678
|
entity |
| Predicate | typicalCases |
P10545
|
FINISHED |
| Object | doping disputes |
—
|
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: doping disputes | Statement: [Court of Arbitration for Sport, typicalCases, doping disputes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalCases Context triple: [Court of Arbitration for Sport, typicalCases, doping disputes]
-
A.
typicalCaseTypes
chosen
Indicates the kinds or categories of cases that are most commonly associated with or handled by a given entity.
-
B.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
C.
typicalPractice
Indicates that an action, behavior, or method is commonly or customarily done in a given context or by a given group.
-
D.
typicalPrecedent
Indicates that one situation, case, or event serves as a standard or commonly followed example for how similar later situations are handled.
-
E.
typicalCircumstance
Indicates the usual or commonly occurring situation, condition, or context in which an event, action, or relationship typically takes place.
- 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_69c008d5ab108190b346c465696824a9 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06745b3d88190bcabc2bf5d75555d |
completed | March 22, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69c060ea1a988190889e47b7e0c819b8 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:31 p.m.