Triple
T6611765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Schumacher |
E149252
|
entity |
| Predicate | firstFerrariWorldTitleSeason |
P72459
|
FINISHED |
| Object | 2000 |
—
|
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: 2000 | Statement: [Michael Schumacher, firstFerrariWorldTitleSeason, 2000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstFerrariWorldTitleSeason Context triple: [Michael Schumacher, firstFerrariWorldTitleSeason, 2000]
-
A.
debutInFormulaOneSeason
Indicates the Formula One season during which an entity (typically a driver or team) made its first official appearance in the championship.
-
B.
lastFormulaOneSeason
Indicates the specific Formula One racing season in which an entity most recently participated or was active.
-
C.
numberOfFormulaOneTTWorldTitles
Indicates the count of Formula One TT World Championship titles that an entity has won.
-
D.
firstFormulaOneGrandPrix
Indicates the event at which an entity made its debut participation in a Formula One Grand Prix.
-
E.
firstEditionSeason
Indicates the season or time period during which something (such as a work or product) was first published, released, or issued in its original edition.
- F. None of above. chosen
Provenance (4 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_69c687ebc680819094caf71faba2efe2 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cf3796d08190a26e988386089447 |
completed | March 27, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69c6acfed25481909cac74c84a9fe088 |
completed | March 27, 2026, 4:14 p.m. |
| PDg | Predicate description generation | batch_69c6cf3683d08190b19e2aad30f2800f |
completed | March 27, 2026, 6:40 p.m. |
Created at: March 27, 2026, 1:57 p.m.