Triple
T38156493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dior haute couture collections |
E952900
|
entity |
| Predicate | predecessorDesigner |
P97
|
FINISHED |
| Object | Raf Simons |
—
|
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: Raf Simons | Statement: [Dior haute couture collections, predecessorDesigner, Raf Simons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorDesigner Context triple: [Dior haute couture collections, predecessorDesigner, Raf Simons]
-
A.
predecessorDesign
Indicates that one design serves as the predecessor or earlier version in relation to another design.
-
B.
predecessorName
Indicates that the value is the name of an entity that directly precedes another in an ordered sequence or lineage.
-
C.
predecessor
chosen
Indicates that one entity comes before another in an ordered sequence or succession.
-
D.
predecessorModel
Indicates that one model directly precedes another in a sequence, version history, or developmental lineage.
-
E.
predecessorUser
Indicates that one user previously held a role, position, or state that is now held by another user, making the first user the predecessor of the second.
- 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_69f76f0a67f4819080c492f61d688fcc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fe8ddf70e48190a917eb9e8f7b6966 |
completed | May 9, 2026, 1:29 a.m. |
| PD | Predicate disambiguation | batch_69fe87ef94dc81909bb00ec8d6de9bcd |
completed | May 9, 2026, 1:03 a.m. |
Created at: May 3, 2026, 4:21 p.m.