Triple
T23013304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Firestone Grand Prix of St. Petersburg |
E572962
|
entity |
| Predicate | tyreSupplier |
P30565
|
FINISHED |
| Object | Firestone |
—
|
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: Firestone | Statement: [Firestone Grand Prix of St. Petersburg, tyreSupplier, Firestone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firestone Context triple: [Firestone Grand Prix of St. Petersburg, tyreSupplier, Firestone]
-
A.
Firestone
Firestone is a small town in Colorado’s Front Range region, known for its residential communities and proximity to the Denver metropolitan area.
-
B.
Firestone
chosen
Firestone is a major American tire brand known for supplying high-performance racing tires, particularly in open-wheel series like IndyCar.
-
C.
Firestone
"Firestone" is a popular electronic dance music track by Norwegian DJ Kygo featuring Australian singer Conrad Sewell on vocals.
-
D.
Dunlop
Dunlop is the middle name of A. D. Lindsay, a British academic and philosopher.
-
E.
Dunlop
Dunlop is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e300008190bb12c6388a8b3280 |
completed | April 29, 2026, 4:06 a.m. |
Created at: April 17, 2026, 3:51 p.m.