Triple
T20025433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Wertingen |
E494969
|
entity |
| Predicate | involvedUnitFrench |
P1063
|
FINISHED |
| Object | French cavalry under Murat |
—
|
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: French cavalry under Murat | Statement: [Battle of Wertingen, involvedUnitFrench, French cavalry under Murat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedUnitFrench Context triple: [Battle of Wertingen, involvedUnitFrench, French cavalry under Murat]
-
A.
FrenchUnit
Indicates that a unit or entity is associated with France, typically by origin, affiliation, or national identity.
-
B.
involvedUnit
chosen
Indicates that a particular unit (such as a group, organization, or division) participates in, is associated with, or plays a role in the referenced event or activity.
-
C.
FrenchOperation
Indicates an operation, mission, or activity that is conducted by, under the authority of, or primarily involving France or French entities.
-
D.
FrenchCasualties
Indicates that the relationship specifies the number or extent of casualties suffered by French forces in a given event or context.
-
E.
joinedFrance
Indicates that an entity became a member of or was incorporated into France.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6628d5b8c8190a35f95ac4a016550 |
completed | April 20, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69e54ce752748190a0a1ffddd0372271 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:35 p.m.