Triple
T38358742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Grand Prix |
E1046407
|
entity |
| Predicate | hasHostedCategory |
P197222
|
FINISHED |
| Object | Formula One |
—
|
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: Formula One | Statement: [South African Grand Prix, hasHostedCategory, Formula One]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHostedCategory Context triple: [South African Grand Prix, hasHostedCategory, Formula One]
-
A.
hasHostedVenue
Indicates that a particular venue has served as the location for hosting a specific event or activity.
-
B.
hasHostedPerformer
Indicates that a venue or event has served as the host location where a particular performer has appeared or given a performance.
-
C.
hasHostedSport
Indicates that a place or organization has served as the venue or organizer for one or more sporting events.
-
D.
hasBeenHostedIn
Indicates that an event, show, or activity took place or was conducted at a particular location or venue in the past.
-
E.
hasBeenHostOf
Indicates that an entity has previously served in the role of host for another entity, such as an event, show, or program.
- 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_69f76e3a94fc81908edc175e8d259e80 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe7bfc94bc81909eeec946e8c1c450 |
completed | May 9, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69fe7b74a1188190886f128e07f712da |
completed | May 9, 2026, 12:10 a.m. |
| PDg | Predicate description generation | batch_69fe7bfb71b08190bed5c33e4ab7afff |
completed | May 9, 2026, 12:12 a.m. |
Created at: May 3, 2026, 4:31 p.m.