Triple
T11795549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Battalion 303 |
E280495
|
entity |
| Predicate | unitComposition |
P101620
|
FINISHED |
| Object | German policemen |
—
|
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 policemen | Statement: [Police Battalion 303, unitComposition, German policemen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitComposition Context triple: [Police Battalion 303, unitComposition, German policemen]
-
A.
componentUnit
Indicates that one entity functions as a constituent or sub-unit that forms part of a larger composite entity.
-
B.
unitOfMeasure
Indicates that one entity specifies the standard unit in which the quantity or value of another entity is measured.
-
C.
unitSystem
Indicates the system of measurement units (such as metric or imperial) that is used to quantify associated values or attributes.
-
D.
isAUnitOf
Indicates that one entity functions as a unit or standard measure in which the other entity is quantified or expressed.
-
E.
designationUnit
Indicates that one entity serves as the unit or standard of measure used to designate, label, or quantify another entity.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5a1cda0819092d66a82fd882786 |
completed | April 10, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69d8a2491f048190853239bc05090bf4 |
completed | April 10, 2026, 7:10 a.m. |
| PDg | Predicate description generation | batch_69d8a43cc0c881909fed7cd759fe90b1 |
completed | April 10, 2026, 7:18 a.m. |
Created at: April 8, 2026, 9:42 p.m.