Triple
T36838820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MagentaZuhause |
E910346
|
entity |
| Predicate | customerSupportProvider |
P174771
|
FINISHED |
| Object | Deutsche Telekom customer service |
—
|
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: Deutsche Telekom customer service | Statement: [MagentaZuhause, customerSupportProvider, Deutsche Telekom customer service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: customerSupportProvider Context triple: [MagentaZuhause, customerSupportProvider, Deutsche Telekom customer service]
-
A.
customerSupport
chosen
Indicates that one entity provides assistance, troubleshooting, or service-related help to another entity.
-
B.
supportStudioCountry
Indicates that a country provides support or backing to a particular studio.
-
C.
technicalContact
Indicates that one entity serves as the primary point of contact for technical issues, support, or maintenance related to another entity.
-
D.
typeOfSupport
Indicates the kind or category of assistance, help, or backing provided in a given context.
-
E.
providesSupportTo
Indicates that one entity offers help, resources, or reinforcement to another entity to aid its function, stability, or success.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.