Triple
T6723201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh law |
E153445
|
entity |
| Predicate | hasDevolvedMatters |
P73347
|
FINISHED |
| Object | health |
—
|
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: health | Statement: [Welsh law, hasDevolvedMatters, health]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDevolvedMatters Context triple: [Welsh law, hasDevolvedMatters, health]
-
A.
hasDevolvedBody
Indicates that authority, responsibility, or powers have been transferred from a central entity to a subordinate or regional entity.
-
B.
hasDevolutionContext
Indicates that something is associated with, or occurs within, a specific context of devolution (such as the transfer or delegation of powers or responsibilities).
-
C.
hasDevolvedParliamentSince
Indicates that a region or country has had its own devolved parliamentary body continuously since the specified time.
-
D.
hasAppealsTo
Indicates that one entity formally challenges or seeks review of a decision, judgment, or outcome through another entity or process.
-
E.
hasDebatedStatus
Indicates that an entity has participated in or been assigned a particular status related to a debate or debating activity.
- 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_69c6880afb988190ad88011b48ecfcba |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d354177481908ab3cf5437c095e2 |
completed | March 27, 2026, 6:58 p.m. |
| PD | Predicate disambiguation | batch_69c6d08e8a2c8190ae4e8d8c039be7ce |
completed | March 27, 2026, 6:46 p.m. |
| PDg | Predicate description generation | batch_69c6d35134148190b49fb5c25a0f8ed4 |
completed | March 27, 2026, 6:58 p.m. |
Created at: March 27, 2026, 2:08 p.m.