Triple
T24391909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Rocroi |
E614914
|
entity |
| Predicate | FrenchSideLedBy |
P19844
|
FINISHED |
| Object | Duc d’Enghien |
—
|
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: Duc d’Enghien | Statement: [Battle of Rocroi, FrenchSideLedBy, Duc d’Enghien]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FrenchSideLedBy Context triple: [Battle of Rocroi, FrenchSideLedBy, Duc d’Enghien]
-
A.
FrenchSide
Indicates that an entity is positioned on, associated with, or belongs to the French side of a border, division, or relationship.
-
B.
FrenchFlagship
Indicates that an entity serves as the primary or leading representative (flagship) of France in a given domain or context.
-
C.
FrenchCommander
chosen
Indicates that an entity serves as a military commander associated with France.
-
D.
monarchOfFrenchSide
Indicates that one entity serves as the ruling monarch over the French side or faction in a given context or domain.
-
E.
FrenchRole
Indicates a role or position that an entity holds specifically within a French context (e.g., in France or related to French institutions, culture, or language).
- 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_69e2d7e509b88190a53155d4f3de45ce |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f294595cec819084cbd5d1b0e08731 |
completed | April 29, 2026, 11:29 p.m. |
| PD | Predicate disambiguation | batch_69f287c4a2b48190b80fb7a3c0e9b018 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:04 a.m.