Triple
T598902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senedd |
E11448
|
entity |
| Predicate | legislativeLanguage |
P13286
|
FINISHED |
| Object | Welsh |
—
|
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: Welsh | Statement: [Senedd, legislativeLanguage, Welsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legislativeLanguage Context triple: [Senedd, legislativeLanguage, Welsh]
-
A.
languageOfLegislature
chosen
Indicates the language or languages officially used by a legislature to conduct its proceedings, draft laws, and perform its formal functions.
-
B.
legislature
Indicates that an entity serves as, or is part of, a law-making body or assembly responsible for creating or amending laws for a political unit.
-
C.
legislativeArticle
Indicates a relationship where one entity is a specific article or clause within a legislative or legal document that governs or regulates another entity.
-
D.
typeOfLegislation
Indicates the specific category or kind of legislation that a given legal act or measure belongs to.
-
E.
legislativeRole
Indicates that an entity holds or performs a specific official position, function, or duty within a legislative body or lawmaking process.
- 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_69a4932779b881908688590d59c71900 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49dc4f7d08190990f70b9b3af6ce5 |
completed | March 1, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69a49cf59cd0819084e67981cb371e25 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.