Triple
T35758211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ford-Cosworth BDA engine |
E1033502
|
entity |
| Predicate | blockOrigin |
P183634
|
FINISHED |
| Object | Ford Kent engine block |
—
|
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: Ford Kent engine block | Statement: [Ford-Cosworth BDA engine, blockOrigin, Ford Kent engine block]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: blockOrigin Context triple: [Ford-Cosworth BDA engine, blockOrigin, Ford Kent engine block]
-
A.
holderOrigin
Indicates that one entity is the original source, creator, or origin point from which the holder entity derives, is issued, or established.
-
B.
originProtectedStatus
Indicates that an entity’s original source or location is subject to protection, restriction, or special safeguarding status.
-
C.
actionOrigin
Indicates the source or starting point from which an action is initiated or originates.
-
D.
borderStateOrigin
Indicates that a state shares a land or maritime border with the place where an entity originated.
-
E.
originPolicy
Indicates the rule or principle that governs how something originates from, is derived from, or is associated with a particular source or starting point.
- F. None of above. chosen
Provenance (4 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a1f64f1081908cc2774840684310 |
completed | May 3, 2026, 7:28 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a162672481909773f8383d91159a |
completed | May 3, 2026, 7:26 p.m. |
Created at: May 3, 2026, 4:06 p.m.