Triple
T2630392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DBX |
E59617
|
entity |
| Predicate | underlyingCompanyServices |
P35149
|
FINISHED |
| Object | cloud-based file storage |
—
|
LITERAL 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-based file storage | Statement: [DBX, underlyingCompanyServices, cloud-based file storage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underlyingCompanyServices Context triple: [DBX, underlyingCompanyServices, cloud-based file storage]
-
A.
underlyingCompanyService
chosen
Indicates that one entity functions as a foundational or supporting service for another company or business entity.
-
B.
underlyingCompany
Indicates that one entity serves as the fundamental or base company upon which another entity (such as a product, instrument, or structure) is built, derived, or dependent.
-
C.
serviceOf
Indicates that one entity performs, provides, or fulfills a function or duty on behalf of another entity.
-
D.
underlyingCompanyName
Indicates the name of the company that serves as the foundational or primary entity underlying another entity, structure, or instrument.
-
E.
serviceFor
Indicates that one entity provides a service or performs functions on behalf of another entity.
- 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_69ab4ac8596c8190b34997e73d9e991c |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abdb0e7b888190bfa5d2e33f00ec0f |
completed | March 7, 2026, 8 a.m. |
| PD | Predicate disambiguation | batch_69abd810d7f481908e81c305772c4c14 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:50 p.m.