Triple
T25018371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dreyse needle gun |
E626202
|
entity |
| Predicate | massProducedBy |
P4022
|
FINISHED |
| Object | Prussian state arsenals |
—
|
NE NERFINISHED |
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: Prussian state arsenals | Statement: [Dreyse needle gun, massProducedBy, Prussian state arsenals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: massProducedBy Context triple: [Dreyse needle gun, massProducedBy, Prussian state arsenals]
-
A.
massProduced
Indicates that an item is manufactured in large quantities, typically using standardized, industrial production processes.
-
B.
manufacturedBy
chosen
Indicates that an item or product is produced or created by a specific manufacturer or maker.
-
C.
makerOf
Indicates that one entity is the creator, producer, or manufacturer of another entity.
-
D.
madeBy
Indicates that something is created, produced, or brought into existence by a particular agent or source.
-
E.
wasFirstProducedBy
Indicates that something (such as a product, work, or item) was initially created, manufactured, or brought into existence by a particular agent, organization, or producer.
- 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_69e2ff27755881908490178e83701160 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f44ba7f8dc81908b4e7659d95f99be |
completed | May 1, 2026, 6:43 a.m. |
| PD | Predicate disambiguation | batch_69f442c0c2e88190acd7f170f10ccef6 |
completed | May 1, 2026, 6:05 a.m. |
Created at: April 18, 2026, 6:06 a.m.