Triple
T9990318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | former Stasi remand prison Berlin-Hohenschönhausen |
E196868
|
entity |
| Predicate | hasLanguageOfExhibitions |
P91455
|
FINISHED |
| Object | German |
—
|
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: German | Statement: [former Stasi remand prison Berlin-Hohenschönhausen, hasLanguageOfExhibitions, German]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageOfExhibitions Context triple: [former Stasi remand prison Berlin-Hohenschönhausen, hasLanguageOfExhibitions, German]
-
A.
hasExhibitionsAbout
Indicates that one entity organizes or presents exhibitions whose subject matter concerns another entity.
-
B.
hasExhibits
Indicates that an entity (such as a museum, gallery, or event) displays or presents certain items, artworks, or objects as part of its collection or show.
-
C.
hasExhibition
Indicates that an entity organizes, hosts, or presents a particular exhibition.
-
D.
hasExhibitionScope
Indicates the thematic, geographic, temporal, or conceptual range and boundaries that define what an exhibition covers.
-
E.
hasExhibitedAt
Indicates that an entity has displayed or presented its work at a particular event, venue, or exhibition.
- F. None of above. chosen
Provenance (4 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdc7a0cb6481908d7bd1b43f93bd18 |
completed | April 2, 2026, 1:34 a.m. |
| PD | Predicate disambiguation | batch_69cd1da07db88190945bcdab3ca82e71 |
completed | April 1, 2026, 1:29 p.m. |
| PDg | Predicate description generation | batch_69cd358386f48190833c862b5b8c04b2 |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:50 p.m.