Triple
T12512210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Pascal |
E299106
|
entity |
| Predicate | formerWorldChampionIn |
P21542
|
FINISHED |
| Object | light heavyweight |
—
|
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: light heavyweight | Statement: [Jean Pascal, formerWorldChampionIn, light heavyweight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerWorldChampionIn Context triple: [Jean Pascal, formerWorldChampionIn, light heavyweight]
-
A.
featuredWorldChampion
Indicates that an entity has been highlighted or showcased specifically in its capacity as a world champion.
-
B.
worldChampionPredecessor
Indicates that one entity was the immediate previous world champion before another entity.
-
C.
worldChampionIn
chosen
Indicates that an entity holds or has held the title of world champion in a specified field, discipline, or competition.
-
D.
notableFormerChampion
Indicates that an entity was once a champion of something and is recognized as particularly distinguished or prominent in that former champion role.
-
E.
formerWorldNo1
Indicates that the subject was ranked number one in the world in the past, but does not hold that top ranking currently.
- 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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d954b867dc8190af8a70f797e4d133 |
completed | April 10, 2026, 7:51 p.m. |
| PD | Predicate disambiguation | batch_69d954096af88190b6be81b008c82139 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 8, 2026, 9:57 p.m.