Triple
T23448527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RMS |
E565609
|
entity |
| Predicate | associatedCompanyFoundedAsBrand |
P1501
|
FINISHED |
| Object | Hermès |
—
|
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: Hermès | Statement: [RMS, associatedCompanyFoundedAsBrand, Hermès]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedCompanyFoundedAsBrand Context triple: [RMS, associatedCompanyFoundedAsBrand, Hermès]
-
A.
associatedCompanyFoundedAs
Indicates that one company was originally established or created under a former name or organizational form that is now associated with the current company.
-
B.
associatedCompanyFoundedIn
Indicates that the related company was founded in the specified year or time period.
-
C.
associatedCompanyFormerlyIndependent
Indicates that the associated company was once an independent entity before becoming linked to or integrated with another organization.
-
D.
formerBrand
chosen
Indicates that an entity was previously used or recognized as a brand for another entity but is no longer its current brand.
-
E.
brandMergedWith
Indicates that two previously distinct brands have combined into a single unified brand entity, typically through merger or acquisition.
- 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_69e24584f9488190bb32730bd2ce023e |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a64b27988190b4722425da964407 |
completed | April 29, 2026, 6:33 a.m. |
| PD | Predicate disambiguation | batch_69f06201d33481909b5fd7b92d03e658 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 5:52 p.m.