Triple
T15773629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verband der Deutschen Buchdrucker |
E382425
|
entity |
| Predicate | unionPosition |
P54811
|
FINISHED |
| Object | Tarifverhandlungen im Druckgewerbe |
—
|
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: Tarifverhandlungen im Druckgewerbe | Statement: [Verband der Deutschen Buchdrucker, unionPosition, Tarifverhandlungen im Druckgewerbe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unionPosition Context triple: [Verband der Deutschen Buchdrucker, unionPosition, Tarifverhandlungen im Druckgewerbe]
-
A.
union
Indicates that two or more sets are combined into a single set containing all elements that belong to at least one of them.
-
B.
memberUnion
Indicates that an entity is a member (part of) a specified union or collective group.
-
C.
unionStrength
Indicates the degree of solidarity, cohesion, or collective power within or among unions or union members.
-
D.
unionRepresents
chosen
Indicates that one entity serves as the official representative or acting body on behalf of a union in relation to another entity or context.
-
E.
unionGoal
Indicates that the entities share a common objective or outcome they aim to achieve together as a unified group.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e051976d248190adddd3db9f758e22 |
completed | April 16, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69e00531e7ac8190a4190cce4f7fab4c |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:47 a.m.