Triple
T548324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wales Millennium Centre |
E12780
|
entity |
| Predicate | façadeInscriptionLanguage |
P4196
|
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: [Wales Millennium Centre, façadeInscriptionLanguage, Welsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: façadeInscriptionLanguage Context triple: [Wales Millennium Centre, façadeInscriptionLanguage, Welsh]
-
A.
bellInscriptionLanguage
Indicates the language in which the inscription on a bell is written.
-
B.
hasFrenchSector
Indicates that an entity includes, controls, or is associated with a sector or area designated as French.
-
C.
languageOfSignage
chosen
Indicates the language used on signs or written displays associated with an entity.
-
D.
inscriptionTranslation
Indicates that a provided text expresses the translated content of a specific inscription.
-
E.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
- 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_69a49334226c81908b0ea1689ef6aa3f |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49900895c819092a131c185a758bf |
completed | March 1, 2026, 7:52 p.m. |
| PD | Predicate disambiguation | batch_69a494b957988190bc269e372df2f0b2 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.