Triple
T35075788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ronan & Erwan Bouroullec |
E1012305
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Cloud shelving system
The Cloud shelving system is a modular, cloud-shaped storage unit designed by Ronan and Erwan Bouroullec that can be combined in various configurations to create sculptural, customizable shelving.
|
E2124008
|
NE 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: Cloud shelving system | Statement: [Ronan & Erwan Bouroullec, notableWork, Cloud shelving system]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cloud shelving system Triple: [Ronan & Erwan Bouroullec, notableWork, Cloud shelving system]
Generated description
The Cloud shelving system is a modular, cloud-shaped storage unit designed by Ronan and Erwan Bouroullec that can be combined in various configurations to create sculptural, customizable shelving.
Provenance (5 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_69f76dd32c008190853aef6028f60208 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7865b4684819093f95e659522b75e |
completed | May 3, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37c648b77081908351ce57d8155c57 |
completed | June 21, 2026, 11:08 a.m. |
| NEDg | Description generation | batch_6a37c6ea4f688190bfc3c69da98aefe4 |
completed | June 21, 2026, 11:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a37c7e9f2e4819081f46285fb314fa4 |
completed | June 21, 2026, 11:15 a.m. |
Created at: May 3, 2026, 4:01 p.m.