Triple
T22227593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RGU SPORT |
E549384
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | RGU SPORT |
—
|
NE NERFINISHED |
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: RGU SPORT | Statement: [RGU SPORT, name, RGU SPORT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RGU SPORT Context triple: [RGU SPORT, name, RGU SPORT]
-
A.
RGU SPORT
chosen
RGU SPORT is Robert Gordon University's dedicated sports and fitness centre located on its Garthdee campus in Aberdeen, Scotland.
-
B.
RGU
RGU is the abbreviated name of Rakuno Gakuen University, a Japanese institution known for its focus on agriculture, veterinary medicine, and life sciences.
-
C.
RGU:Union
RGU:Union is the students' association representing and supporting the student body at Robert Gordon University in Aberdeen, Scotland.
-
D.
sportscotland
sportscotland is the national agency for sport in Scotland, responsible for developing and promoting sport and physical activity across the country.
-
E.
RUGL
RUGL is the data vendor code used to identify the Russell Global Index, a comprehensive benchmark covering global equity markets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12befe38c8190b547586e41b099b1 |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:37 p.m.