Triple
T23121729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Mars-la-Tour |
E576910
|
entity |
| Predicate | objectivePrussia |
P17252
|
FINISHED |
| Object | cut French line of retreat from Metz |
—
|
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: cut French line of retreat from Metz | Statement: [Battle of Mars-la-Tour, objectivePrussia, cut French line of retreat from Metz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: objectivePrussia Context triple: [Battle of Mars-la-Tour, objectivePrussia, cut French line of retreat from Metz]
-
A.
PrussianObjective
chosen
Indicates that an entity has the goal, target, or strategic objective of achieving or advancing something specifically related to Prussia or Prussian interests.
-
B.
objectiveGermany
Indicates that an entity has Germany as its objective, target, or goal in a given context.
-
C.
mainOpponentOfPrussia
Indicates that one entity serves as the primary adversary or principal opposing force to Prussia in a given conflict or rivalry.
-
D.
objectivePoland
Indicates that something has Poland as its goal, target, or intended destination.
-
E.
outcomeForPrussia
Indicates the result or consequence that an event, action, or situation has specifically for 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e50c500819095d59aef44388153 |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.