Triple
T27957503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verkehrsministerium |
E703590
|
entity |
| Predicate | arbeitetMit |
P398
|
FINISHED |
| Object | Verkehrsunternehmen |
—
|
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: Verkehrsunternehmen | Statement: [Verkehrsministerium, arbeitetMit, Verkehrsunternehmen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: arbeitetMit Context triple: [Verkehrsministerium, arbeitetMit, Verkehrsunternehmen]
-
A.
worksWith
chosen
Indicates that two entities collaborate or perform tasks together in a shared work-related context.
-
B.
worksFor
Indicates that one entity is employed by or performs work on behalf of another entity, typically an organization or individual.
-
C.
partnerInWorkOf
Indicates a collaborative relationship where one entity works together with another on a shared task, project, or professional activity.
-
D.
basedManyWorksOn
Indicates that an entity is founded or established upon the contributions or results of many different works.
-
E.
workWith
Indicates that one entity collaborates or engages in work-related activities together with 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_69ef840c8b2c8190946ae9522774ba51 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f64dbbaefc8190952b8320bf4397d8 |
completed | May 2, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 7:29 p.m.