Triple
T35907021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citroën Break |
E1038499
|
entity |
| Predicate | partOfModelFamily |
P202743
|
FINISHED |
| Object | Citroën DS range |
—
|
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: Citroën DS range | Statement: [Citroën Break, partOfModelFamily, Citroën DS range]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfModelFamily Context triple: [Citroën Break, partOfModelFamily, Citroën DS range]
-
A.
partOfBrandPortfolioOf
Indicates that one brand is included within, and belongs to, the overall brand portfolio of another entity.
-
B.
usesSameBrandFamilyAs
Indicates that two entities use products or services belonging to the same overarching brand family or brand portfolio.
-
C.
isBrandFamilyOf
Indicates that one brand belongs to, or is part of, a broader brand family or umbrella brand.
-
D.
introducedModelFamily
Indicates that an entity (such as a person or organization) is responsible for first presenting or launching a particular model family.
-
E.
supportsModelFamily
Indicates that one entity provides compatibility, functionality, or resources necessary for the operation or use of a particular model family.
- 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a00b34364448190b8c9948d5a24d845 |
completed | May 10, 2026, 4:33 p.m. |
| PD | Predicate disambiguation | batch_6a00b2e4f13c819081bac7d763c414ad |
completed | May 10, 2026, 4:31 p.m. |
| PDg | Predicate description generation | batch_6a00b342b39c8190b54d6d85ddafb085 |
completed | May 10, 2026, 4:33 p.m. |
Created at: May 3, 2026, 4:07 p.m.