Triple
T18536178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Lady of Germany |
E452970
|
entity |
| Predicate | canBeVacantIf |
P35080
|
FINISHED |
| Object | President of Germany is unmarried |
—
|
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: President of Germany is unmarried | Statement: [First Lady of Germany, canBeVacantIf, President of Germany is unmarried]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeVacantIf Context triple: [First Lady of Germany, canBeVacantIf, President of Germany is unmarried]
-
A.
canBeVacantWhen
chosen
Indicates the conditions or circumstances under which something is allowed or able to remain unoccupied or empty.
-
B.
canBeVacant
Indicates that an entity (such as a position, property, or role) is capable of being unoccupied or without an assigned holder.
-
C.
canBeVacated
Indicates that a position, status, or decision is capable of being annulled, set aside, or rendered void.
-
D.
canBeEmpty
Indicates that something is allowed or able to have no content, elements, or value.
-
E.
canBeDisabledOn
Indicates that a feature, function, or capability has the property that it can be turned off or deactivated when applied to the referenced 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_69d8d387b5548190aa030dad2cb4947e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5340256d08190bf22d2cb064413b2 |
completed | April 19, 2026, 7:58 p.m. |
| PD | Predicate disambiguation | batch_69e469e0025c81908f16ed4f922674af |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:37 a.m.