Triple
T6343062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Court of Arbitration for Sport |
E142678
|
entity |
| Predicate | oftenActsAs |
P24836
|
FINISHED |
| Object | final court of appeal in sports 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: final court of appeal in sports disputes | Statement: [Court of Arbitration for Sport, oftenActsAs, final court of appeal in sports disputes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenActsAs Context triple: [Court of Arbitration for Sport, oftenActsAs, final court of appeal in sports disputes]
-
A.
actsOn
Indicates that one entity performs an action that affects, targets, or is directed toward another entity.
-
B.
oftenBroadcastAs
Indicates that something is frequently transmitted or aired through a broadcast medium under a particular form, title, or version.
-
C.
appearsAs
chosen
Indicates that one entity is presented, perceived, or manifested in the form, role, or guise of another entity.
-
D.
actsOnBehalfOf
Indicates that one entity performs actions or makes decisions as a representative or proxy for another entity.
-
E.
oftenInvolvedWith
Indicates that one entity frequently participates in or is commonly associated with activities, events, or situations involving another entity.
- 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.