Triple
T35752437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Austrian Grand Prix |
E1033351
|
entity |
| Predicate | followingRace |
P195064
|
FINISHED |
| Object | 2016 British Grand Prix |
—
|
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: 2016 British Grand Prix | Statement: [2016 Austrian Grand Prix, followingRace, 2016 British Grand Prix]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followingRace Context triple: [2016 Austrian Grand Prix, followingRace, 2016 British Grand Prix]
-
A.
racesOn
Indicates that one entity participates in a race or competitive running event that takes place on or along another entity (such as a track, course, or surface).
-
B.
precedingRace
chosen
Indicates that one race occurs or is scheduled before another race in a temporal sequence.
-
C.
raceMeeting
Indicates a competitive event where multiple participants race against each other under shared rules and conditions.
-
D.
lastRace
Indicates that one race is the final or most recent race in a sequence or series of races.
-
E.
nextTournament
Indicates that one entity is the immediately upcoming tournament scheduled to occur for 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_69ff1c91bbac8190b84012dee1cb3b2c |
completed | May 9, 2026, 11:37 a.m. |
| PD | Predicate disambiguation | batch_69ff1c23ca508190bb5a435d765b7e53 |
completed | May 9, 2026, 11:36 a.m. |
Created at: May 3, 2026, 4:06 p.m.