Triple
T27642929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garmin-Slipstream |
E696632
|
entity |
| Predicate | hadRider |
P59648
|
FINISHED |
| Object | David Zabriskie |
—
|
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: David Zabriskie | Statement: [Garmin-Slipstream, hadRider, David Zabriskie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadRider Context triple: [Garmin-Slipstream, hadRider, David Zabriskie]
-
A.
hadFort
Indicates that an entity possessed, controlled, or contained a fort at some time.
-
B.
laterRider
Indicates that one rider or passenger occurs or appears later in time than another rider or passenger within a given context or sequence.
-
C.
hasOwnerRider
Indicates that an entity (such as an animal or vehicle) has a specific person who both owns it and rides or uses it.
-
D.
isRiddenBy
chosen
Indicates that an entity serves as a mount or vehicle that is being ridden by another entity.
-
E.
riderType
Indicates the category or role of a rider in relation to a ride, transport service, or vehicle (e.g., passenger, driver, courier).
- 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63894e5848190aec428392562ab06 |
completed | May 2, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 2:27 p.m.