Triple
T15395114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bradley Wiggins |
E368157
|
entity |
| Predicate | team |
P3756
|
FINISHED |
| Object | Cofidis |
E696631
|
NE 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: Cofidis | Statement: [Bradley Wiggins, team, Cofidis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cofidis Context triple: [Bradley Wiggins, team, Cofidis]
-
A.
Cofidis cycling team
chosen
Cofidis is a professional road cycling team from France known for competing in major international races such as the Tour de France.
-
B.
Orica
Orica is a municipality in central Honduras known for its rural communities and agricultural activities within the Francisco Morazán Department.
-
C.
Peugeot cycling team
The Peugeot cycling team was a prominent professional road cycling squad from France, active for much of the 20th century and known for nurturing numerous champions and pioneering sponsorship in the sport.
-
D.
Agalev
Agalev was the original name of the Flemish green political party now known as Groen in Belgium.
-
E.
Audeca
Audeca was the last king of the Suebic Kingdom in Gallaecia, whose brief reign in the late 6th century ended with the annexation of his realm by the Visigothic Kingdom.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e8ac79081908ac79c0b3e7587ff |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff13523f548190beafd130f8741465 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:19 a.m.