Triple
T35753392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coppa Acerbo |
E1033374
|
entity |
| Predicate | 1957F1RaceWinner |
P122398
|
FINISHED |
| Object | Stirling Moss |
—
|
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: Stirling Moss | Statement: [Coppa Acerbo, 1957F1RaceWinner, Stirling Moss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 1957F1RaceWinner Context triple: [Coppa Acerbo, 1957F1RaceWinner, Stirling Moss]
-
A.
firstWinningDrivers
Indicates the relationship where certain drivers are the first to achieve a race victory within a given context (such as a series, season, team, or event).
-
B.
numberOfF1WorldChampionships
Indicates the number of Formula 1 World Championship titles that an entity has won.
-
C.
grandPrixWin
chosen
Indicates that an entity has achieved victory in a Grand Prix event or race.
-
D.
firstFormulaOneWin
Indicates that the subject achieved their first victory in a Formula One race in relation to the specified event or context.
-
E.
achievedFirstF1PodiumWith
Indicates that one entity secured their first-ever Formula 1 podium finish while driving for or in association with the other 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a198e24881909cc292e420269a8c |
completed | May 3, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.