Triple
T34976671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château-Salins |
E1008693
|
entity |
| Predicate | regionHistoricConflict |
P120570
|
FINISHED |
| Object | Franco-Prussian War area |
—
|
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: Franco-Prussian War area | Statement: [Château-Salins, regionHistoricConflict, Franco-Prussian War area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionHistoricConflict Context triple: [Château-Salins, regionHistoricConflict, Franco-Prussian War area]
-
A.
partOfHistoricalConflict
chosen
Indicates that one entity participated in, belonged to, or was involved as a component of a larger historical conflict or war.
-
B.
linkedToHistoricalConflict
Indicates that one entity has a documented association or connection with a past historical conflict involving another entity.
-
C.
hasHistoricalPeriodOfConflict
Indicates that there exists a specific historical period during which the related entities were engaged in conflict or hostilities.
-
D.
opponentInHistoricalConflict
Indicates that two entities stood on opposing sides in a specific historical conflict or war.
-
E.
loreConflict
Indicates that there is an inconsistency, contradiction, or incompatibility between pieces of lore or canonical information.
- 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_69f76dc78a308190a1ac29ad4a9a4895 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ffa9677be08190852c8ef6c2545fed |
completed | May 9, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69ffa6570e2c8190a9d7b37f12b91d9a |
completed | May 9, 2026, 9:25 p.m. |
Created at: May 3, 2026, 4:01 p.m.