Triple
T12381100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Ministry of Tourism |
E295744
|
entity |
| Predicate | sectorOverlap |
P11740
|
FINISHED |
| Object | culture sector |
—
|
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: culture sector | Statement: [Federal Ministry of Tourism, sectorOverlap, culture sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectorOverlap Context triple: [Federal Ministry of Tourism, sectorOverlap, culture sector]
-
A.
geographicOverlap
Indicates that two geographic areas share at least part of the same physical space or territory.
-
B.
hasJurisdictionOverlapWith
Indicates that two authorities or entities share some portion of legal or regulatory control over the same area, subject, or set of activities.
-
C.
fieldIntersection
chosen
Indicates that two or more fields or domains share a common overlapping area or set of elements.
-
D.
sectorIncludes
Indicates that a broader sector encompasses or contains a specified sub-sector, area, or component within its scope.
-
E.
sectorBase
Indicates that one entity serves as the primary base or foundational location for operations within a particular sector of 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbb3a2481908c2fcb5e6488eb3c |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.