Triple
T1899590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Günter Schabowski |
E37660
|
entity |
| Predicate | laterLifeEvent |
P32941
|
FINISHED |
| Object | expressed regret for GDR border regime |
—
|
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: expressed regret for GDR border regime | Statement: [Günter Schabowski, laterLifeEvent, expressed regret for GDR border regime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterLifeEvent Context triple: [Günter Schabowski, laterLifeEvent, expressed regret for GDR border regime]
-
A.
lifeStatus
Indicates the current state of an entity’s existence, such as whether it is alive, dead, or in another defined life condition.
-
B.
laterLivedIn
Indicates that one entity resided in a particular place during a later period of its life, after an earlier residence elsewhere.
-
C.
lifeStage
Indicates the specific phase or period in an entity’s development or lifecycle that it is currently in.
-
D.
legacyPlanning
Indicates the process of arranging how assets, responsibilities, and wishes will be managed and transferred to others in the future, typically after one’s death.
-
E.
spentMostOfLifeIn
Indicates that an entity resided or was primarily based in a particular place for the majority of its lifetime.
- 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_69a8861be7148190a680937ec451a304 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb17181b0819090683c55fd1352cb |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe7e7e88190b58c0df59187c0c2 |
completed | March 7, 2026, 4:56 a.m. |
| PDg | Predicate description generation | batch_69abb09b27e88190bff164040fef6d7e |
completed | March 7, 2026, 4:59 a.m. |
Created at: March 4, 2026, 7:35 p.m.