Triple
T2911613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aggregat 4 |
E63693
|
entity |
| Predicate | manufacturedUsing |
P21333
|
FINISHED |
| Object | forced labor from Mittelbau-Dora concentration camp |
—
|
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: forced labor from Mittelbau-Dora concentration camp | Statement: [Aggregat 4, manufacturedUsing, forced labor from Mittelbau-Dora concentration camp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: manufacturedUsing Context triple: [Aggregat 4, manufacturedUsing, forced labor from Mittelbau-Dora concentration camp]
-
A.
manufacturedBy
Indicates that an item or product is produced or created by a specific manufacturer or maker.
-
B.
madeWith
chosen
Indicates that one entity is created, produced, or constructed using another entity as a material, ingredient, or component.
-
C.
usedByManufacturer
Indicates that a manufacturer makes use of a particular resource, component, method, or tool in its production or operational processes.
-
D.
madeBy
Indicates that something is created, produced, or brought into existence by a particular agent or source.
-
E.
fabricatedOn
Indicates that something was manufactured, constructed, or produced at a specific time or date.
- 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_69ab4c44ab448190b9411324e8a1fc1d |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe0ea0ae4819096f17d74072b0b78 |
completed | March 7, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_69abdd1b77608190b20fc078fdb85e64 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:11 p.m.