Triple
T13569339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannes Rau |
E324116
|
entity |
| Predicate | termEndAsPresidentOfGermany |
P74950
|
FINISHED |
| Object | 2004 |
—
|
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: 2004 | Statement: [Johannes Rau, termEndAsPresidentOfGermany, 2004]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termEndAsPresidentOfGermany Context triple: [Johannes Rau, termEndAsPresidentOfGermany, 2004]
-
A.
endTime (President of Germany)
chosen
Indicates the date and time at which a person’s term as President of Germany concludes.
-
B.
formerChancellor
Indicates that one entity previously held the position or role of chancellor of the other entity, but no longer does.
-
C.
termEndAsAmbassadorToGermany
Indicates that an entity’s service as ambassador to Germany has concluded at a specified time or under specified conditions.
-
D.
officeEnd (Chancellor of Germany)
Indicates the date or point in time when an individual's term as Chancellor of Germany comes to an end.
-
E.
startTime (President of Germany)
Indicates the point in time at which a person’s term as President of Germany begins.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb00f5b8881908617f42d227ed137 |
completed | April 12, 2026, 2:45 p.m. |
| PD | Predicate disambiguation | batch_69dbae161a0481909f9d3f40ca4e0ac5 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:48 p.m.