Triple
T1704702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basic Law for the Federal Republic of Germany |
E36845
|
entity |
| Predicate | preambleMentions |
P831
|
FINISHED |
| Object | German unity |
—
|
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 unity | Statement: [Basic Law for the Federal Republic of Germany, preambleMentions, German unity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preambleMentions Context triple: [Basic Law for the Federal Republic of Germany, preambleMentions, German unity]
-
A.
preambleRecalls
Indicates that a preamble references or brings back into consideration a prior statement, event, or context.
-
B.
preambleBeginsWith
Indicates that the preamble of a document or text starts with a specified substring, phrase, or content.
-
C.
mentions
chosen
Indicates that one entity refers to, cites, or brings up another entity in some form of communication or content.
-
D.
preambleRecognizes
Indicates that one entity formally acknowledges or accepts the existence, validity, or authority of another within an introductory or preliminary context.
-
E.
preamblePresent
Indicates that a document, statement, or agreement includes an introductory preamble section.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab75ad24408190814069e6e3ef9e59 |
completed | March 7, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69aa61bad17c8190861b92cfb423f68f |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.