Triple
T13559680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Expédition d’Irlande |
E323870
|
entity |
| Predicate | zoneD’opérations |
P2160
|
FINISHED |
| Object | au large du comté de Cork |
—
|
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: au large du comté de Cork | Statement: [Expédition d’Irlande, zoneD’opérations, au large du comté de Cork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: zoneD’opérations Context triple: [Expédition d’Irlande, zoneD’opérations, au large du comté de Cork]
-
A.
zone
chosen
Indicates that an entity is located within, associated with, or assigned to a particular geographic or conceptual area or zone.
-
B.
fieldOfOperation
Indicates the domain, area, or scope within which an entity operates or carries out its primary activities.
-
C.
zoneBased
Indicates that the relationship or action is determined or constrained by specific geographic or logical zones.
-
D.
FrenchOperation
Indicates an operation, mission, or activity that is conducted by, under the authority of, or primarily involving France or French entities.
-
E.
zoneConcept
Indicates that one entity is associated with, defined by, or operates within a particular zone or conceptual area specified by another entity.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbb9ee3f081909056dc1a92c40b7a |
completed | April 12, 2026, 3:34 p.m. |
| PD | Predicate disambiguation | batch_69dbae13bec4819084c1770638c00ed9 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:47 p.m.