Triple
T9990300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | former Stasi remand prison Berlin-Hohenschönhausen |
E196868
|
entity |
| Predicate | functionDuringGDR |
P85987
|
FINISHED |
| Object | remand prison |
—
|
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: remand prison | Statement: [former Stasi remand prison Berlin-Hohenschönhausen, functionDuringGDR, remand prison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionDuringGDR Context triple: [former Stasi remand prison Berlin-Hohenschönhausen, functionDuringGDR, remand prison]
-
A.
functionDuringEvent
Indicates that a particular function, role, or operation is active or carried out during a specified event.
-
B.
functionDuringEdoPeriod
Indicates that the function, role, or activity occurred specifically during Japan’s Edo period.
-
C.
functionDuringDivision
chosen
Indicates that one entity serves a particular function or role specifically during the process or period of division.
-
D.
executedDuring
Indicates that an action or event was carried out within the temporal span of another specified event or period.
-
E.
functionDuringQing
Indicates that a function, role, or activity occurs or is carried out during the Qing dynasty period.
- 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_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. |
Created at: March 30, 2026, 8:50 p.m.