Triple
T35330748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candy Man |
E1020308
|
entity |
| Predicate | sponsorshipContext |
P82974
|
FINISHED |
| Object | primary sponsor M&M’s on No. 18 car |
—
|
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: primary sponsor M&M’s on No. 18 car | Statement: [Candy Man, sponsorshipContext, primary sponsor M&M’s on No. 18 car]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sponsorshipContext Context triple: [Candy Man, sponsorshipContext, primary sponsor M&M’s on No. 18 car]
-
A.
sponsorshipRenamedFrom
Indicates that a sponsorship currently known by one name previously existed under a different, earlier name.
-
B.
sponsorshipScope
Indicates the extent, boundaries, or specific aspects of an activity, event, or entity that a sponsor’s support or involvement covers.
-
C.
sponsorshipBrand
chosen
Indicates that one entity serves as a sponsoring brand for another entity, typically providing support, funding, or endorsement.
-
D.
sponsorshipName
Indicates the name or title associated with a sponsorship relationship between entities.
-
E.
sponsorshipBrandingSince
Indicates that one entity has been publicly branded or presented as sponsored by another entity starting from a specific point in time and continuing thereafter.
- 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_69f76deacf4481908e7735a5a7715b0a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:03 p.m.