Triple
T9336595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KS Toruń (speedway) |
E224657
|
entity |
| Predicate | homeTrackType |
P3832
|
FINISHED |
| Object | oval dirt track |
—
|
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: oval dirt track | Statement: [KS Toruń (speedway), homeTrackType, oval dirt track]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeTrackType Context triple: [KS Toruń (speedway), homeTrackType, oval dirt track]
-
A.
traditionalHomeKitType
Indicates that something is associated with, or categorized by, a traditional type or classification within the HomeKit ecosystem.
-
B.
homeKitType
Indicates the specific HomeKit category or type assigned to a device or accessory within the HomeKit ecosystem.
-
C.
homeCrowdType
Indicates the type or classification of the crowd that is considered the home or primary audience in a given context.
-
D.
homeGroundType
Indicates the type or category of venue that serves as an entity’s designated home ground.
-
E.
trackType
chosen
Indicates the specific kind or category of track associated with an entity, such as its functional or physical classification.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37f161e481908e23c1ec7e5fcf97 |
completed | April 1, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:40 p.m.