Triple
T31999281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antrìm |
E817078
|
entity |
| Predicate | hasLanguageUsageRegion |
P53840
|
FINISHED |
| Object | Ulster |
—
|
NE NERFINISHED |
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: Ulster | Statement: [Antrìm, hasLanguageUsageRegion, Ulster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageUsageRegion Context triple: [Antrìm, hasLanguageUsageRegion, Ulster]
-
A.
alsoInLanguageRegion
chosen
Indicates that two or more entities are located within or associated with the same language-defined geographic region.
-
B.
hasLanguageOfWiderRegion
Indicates that an entity uses a language that serves as a more widely used or regionally dominant language beyond its immediate local context.
-
C.
hasLanguageInCountry
Indicates that a particular language is used or recognized within a specified country.
-
D.
operatorLanguageRegion
Indicates the geographic region or locale in which an operator’s language is used or applicable.
-
E.
usedForLanguageSpokenIn
Indicates that something (such as a resource, tool, or medium) is used for expressing or communicating a language that is spoken in a particular place or region.
- 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_69f348f8ce388190ae84376b1f348f12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe8f74748c8190bd14a856c057f9f7 |
completed | May 9, 2026, 1:35 a.m. |
| PD | Predicate disambiguation | batch_69fe8e7ed8088190929e0df67aca4de9 |
completed | May 9, 2026, 1:31 a.m. |
Created at: May 1, 2026, 12:14 a.m.