Triple
T37406672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Creative City of Design |
E929150
|
entity |
| Predicate | belongsToSubnetwork |
P26301
|
FINISHED |
| Object | design subnetwork of the UNESCO Creative Cities Network |
—
|
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: design subnetwork of the UNESCO Creative Cities Network | Statement: [Creative City of Design, belongsToSubnetwork, design subnetwork of the UNESCO Creative Cities Network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToSubnetwork Context triple: [Creative City of Design, belongsToSubnetwork, design subnetwork of the UNESCO Creative Cities Network]
-
A.
isSubnetworkOf
chosen
Indicates that one network is a contained, subordinate, or component part of another, larger network.
-
B.
belongsToSubsystem
Indicates that one component or element is a part of, or contained within, a larger subsystem.
-
C.
isSubclusterOf
Indicates that one cluster is a smaller, contained subset within a larger cluster.
-
D.
belongsToSubsector
Indicates that one entity is part of, or classified within, a more specific subsector of a broader sector or industry.
-
E.
belongsToSubfamily
Indicates that one entity is a member of, or classified within, a specific subfamily 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_69f76ebbf79c8190b85bbcf3a6be57e4 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0017dd31d08190aa5e9f72df83733a |
completed | May 10, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_6a0015a1deb88190b9cdaa60455b0a33 |
completed | May 10, 2026, 5:20 a.m. |
Created at: May 3, 2026, 4:16 p.m.