Triple
T22828121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gladys |
E565716
|
entity |
| Predicate | possibleOriginLanguage |
P1754
|
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: [Gladys, possibleOriginLanguage, Welsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleOriginLanguage Context triple: [Gladys, possibleOriginLanguage, Welsh]
-
A.
indirectOriginLanguage
Indicates that something originates from a particular language, not directly but through one or more intermediate languages or sources.
-
B.
hasLanguageOfOrigin
chosen
Indicates that one entity has its origin or source in the language specified by another entity.
-
C.
possibleLanguage
Indicates that an entity could plausibly be expressed, interpreted, or communicated in a given language.
-
D.
possiblyTranslatedFrom
Indicates that one item may be a translation of another, but this relationship is uncertain or not definitively established.
-
E.
originalLanguageContext
Indicates the language in which something was first created or expressed, providing the original linguistic context for its content or meaning.
- 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_69e24585ab1c81909b2b5065d15805d5 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e2914188190be6cdbd8167cd806 |
completed | April 29, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69eed2d117088190acbfe130d84f8627 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:34 p.m.