Triple
T33423273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flat Rock Assembly complex |
E855898
|
entity |
| Predicate | hasFormerCoOwner |
P128181
|
FINISHED |
| Object | Mazda Motor Corporation |
—
|
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: Mazda Motor Corporation | Statement: [Flat Rock Assembly complex, hasFormerCoOwner, Mazda Motor Corporation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFormerCoOwner Context triple: [Flat Rock Assembly complex, hasFormerCoOwner, Mazda Motor Corporation]
-
A.
hasCoOwner
Indicates that an entity shares ownership of something with one or more other entities.
-
B.
hasOwnerWhoLaterOwned
Indicates that an entity is owned by someone who, at a later time, also became the owner of another specified entity.
-
C.
hasOwnerInThePast
chosen
Indicates that an entity was owned by another entity at some time in the past, but not necessarily in the present.
-
D.
canHaveCoOwner
Indicates that an entity is allowed to share ownership with one or more additional owners.
-
E.
hasFormerPatron
Indicates that an entity previously served as a patron or sponsor of another entity, but no longer holds that role.
- 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_69f3496fdf0081908c1aa30870ce518b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd9ff026a48190bfec33deeb3b2c43 |
completed | May 8, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69fd97d805bc8190ba12f429d3ad04c7 |
completed | May 8, 2026, 7:59 a.m. |
Created at: May 1, 2026, 1:36 a.m.