Triple
T28594397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Wikidata |
E723734
|
entity |
| Predicate | supportsReusers |
P203161
|
FINISHED |
| Object | external websites |
—
|
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: external websites | Statement: [Korean Wikidata, supportsReusers, external websites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsReusers Context triple: [Korean Wikidata, supportsReusers, external websites]
-
A.
supportsUsers
Indicates that one entity provides assistance, functionality, or compatibility for the users associated with another entity.
-
B.
supportsUse
Indicates that one entity enables, allows, or is compatible with the use or operation of another entity.
-
C.
supportsShares
Indicates that one entity provides assistance, endorsement, or resources to another entity in the context of shared ownership, shared resources, or jointly held interests.
-
D.
supportsRecreationAt
Indicates that one entity provides facilities, conditions, or resources that enable recreational activities to take place at a specified location.
-
E.
supportedReformer
Indicates that one entity actively endorsed or backed a particular reformer in their efforts or cause.
- F. None of above. chosen
Provenance (4 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_6a01302a80ec8190a27692f09ac38a80 |
completed | May 11, 2026, 1:26 a.m. |
| PD | Predicate disambiguation | batch_6a012fad62308190a53f8b4a071eb245 |
completed | May 11, 2026, 1:23 a.m. |
| PDg | Predicate description generation | batch_6a013029b3a48190884d661f6c622cad |
completed | May 11, 2026, 1:26 a.m. |
Created at: April 28, 2026, 4:21 a.m.