Triple
T6723210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh law |
E153445
|
entity |
| Predicate | hasReservedMatters |
P73348
|
FINISHED |
| Object | foreign affairs |
—
|
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: foreign affairs | Statement: [Welsh law, hasReservedMatters, foreign affairs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReservedMatters Context triple: [Welsh law, hasReservedMatters, foreign affairs]
-
A.
hasReservationIn
Indicates that an entity holds or possesses a reservation at or within a specified place, service, or event.
-
B.
reservedFor
Indicates that something is set aside or allocated specifically for the use, benefit, or purpose of a particular entity or group.
-
C.
hasAppealsTo
Indicates that one entity formally challenges or seeks review of a decision, judgment, or outcome through another entity or process.
-
D.
hasReserveStatus
Indicates that an entity holds a designated reserve or backup status in relation to another entity or role.
-
E.
reservesCasesFor
Indicates that an entity allocates or sets aside specific cases for another entity’s use, handling, or attention.
- 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.