Triple
T35718743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Schweinschädel |
E1032406
|
entity |
| Predicate | commandedByPrussia |
P55425
|
FINISHED |
| Object | Karl von Steinmetz |
—
|
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: Karl von Steinmetz | Statement: [Battle of Schweinschädel, commandedByPrussia, Karl von Steinmetz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandedByPrussia Context triple: [Battle of Schweinschädel, commandedByPrussia, Karl von Steinmetz]
-
A.
mainOpponentOfPrussia
Indicates that one entity serves as the primary adversary or principal opposing force to Prussia in a given conflict or rivalry.
-
B.
timeInKingdomOfPrussia
Indicates that an entity spent a specified period of time within the Kingdom of Prussia.
-
C.
monarchOfPrussiaDuringWar
Indicates the person who held the position of monarch of Prussia during a specified war.
-
D.
commandStructurePrussia
chosen
Indicates the hierarchical command relationships within the Prussian military or administrative structure.
-
E.
associatedRulerTitlePrussia
Indicates a relationship where a ruler’s title is specifically linked to or held in connection with Prussia.
- 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_69f76e102b5881909e5d63a30a5cecbe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd7e364a648190a1e9e1d9fc76e99e |
completed | May 8, 2026, 6:09 a.m. |
| PD | Predicate disambiguation | batch_69fd7bb547608190a3b04dddbca6b8bc |
completed | May 8, 2026, 5:59 a.m. |
Created at: May 3, 2026, 4:05 p.m.