Triple
T21021315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carolina Goldrusher |
E517813
|
entity |
| Predicate | intendedRiderType |
P15668
|
FINISHED |
| Object | families |
—
|
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: families | Statement: [Carolina Goldrusher, intendedRiderType, families]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedRiderType Context triple: [Carolina Goldrusher, intendedRiderType, families]
-
A.
riderType
Indicates the category or role of a rider in relation to a ride, transport service, or vehicle (e.g., passenger, driver, courier).
-
B.
intendedRiderExperience
Indicates the type or quality of experience that is planned or designed for a rider in the context of a ride or transportation service.
-
C.
rideRestriction
Indicates that there is a limitation or rule governing whether, how, or under what conditions one entity may ride or be transported by another.
-
D.
supportsRiderCategory
chosen
Indicates that one entity is capable of accommodating, enabling, or being compatible with a specified rider category.
-
E.
hasRidingAssociation
Indicates an association where one entity is related to another through the act or context of riding (e.g., serving as rider, mount, or riding partner).
- 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5db0b88190ae61ea8b38e8ecf7 |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf274ac81909bbf245627dc8fdc |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:54 p.m.