Triple
T819067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erhard Milch |
E17711
|
entity |
| Predicate | sentenceReducedTo |
P20882
|
FINISHED |
| Object | 15 years imprisonment |
—
|
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: 15 years imprisonment | Statement: [Erhard Milch, sentenceReducedTo, 15 years imprisonment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sentenceReducedTo Context triple: [Erhard Milch, sentenceReducedTo, 15 years imprisonment]
-
A.
reduces
Indicates that one entity causes a decrease in the amount, intensity, degree, or impact of another entity.
-
B.
sentenceOf
Indicates that one entity is a sentence that belongs to, is contained in, or is part of another larger text or document.
-
C.
sentence
Indicates that one entity is a sentence that expresses, contains, or encodes information about another entity.
-
D.
reducedRepresentationOf
Indicates that one entity is a simplified, compressed, or lower-detail version of another entity while preserving its essential information or structure.
-
E.
reducesTo
Indicates that one expression, structure, or state can be transformed or simplified into another, typically more basic or canonical, form.
- 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_69a4937bcaac8190a322524ac6f45a5a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab976094819086d676404d745750 |
completed | March 1, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69a4aa76a7808190ac7fd9ba1a4cebcb |
completed | March 1, 2026, 9:07 p.m. |
| PDg | Predicate description generation | batch_69a4ab9634948190b25ea1b2e34df87d |
completed | March 1, 2026, 9:11 p.m. |
Created at: March 1, 2026, 7:38 p.m.