Triple
T28107798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P Zero |
E710407
|
entity |
| Predicate | notableOEMPartner |
P25917
|
FINISHED |
| Object | Ferrari |
—
|
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: Ferrari | Statement: [P Zero, notableOEMPartner, Ferrari]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableOEMPartner Context triple: [P Zero, notableOEMPartner, Ferrari]
-
A.
notablePartner
Indicates that two entities are or have been significant partners, typically in a prominent or noteworthy personal or professional relationship.
-
B.
notableManufacturer
Indicates that an entity is a well-known or prominent producer or maker of another entity.
-
C.
manufacturerSupportedBy
Indicates that a manufacturer receives backing, assistance, or endorsement from another party.
-
D.
technologyPartner
chosen
Indicates a collaborative relationship where one entity provides technological expertise, products, or services to support or co-develop another entity’s solutions or operations.
-
E.
compatibleBrand
Indicates that one brand is suitable for use with, or functions properly alongside, another brand.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_6a007aa8d3a481908543f9b5d562a90c |
completed | May 10, 2026, 12:31 p.m. |
| PD | Predicate disambiguation | batch_6a007a44996481908688ccfdbc56511d |
completed | May 10, 2026, 12:29 p.m. |
Created at: April 27, 2026, 9:09 p.m.