Triple
T26802205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fortriu |
E671130
|
entity |
| Predicate | sourceLanguageOfName |
P28203
|
FINISHED |
| Object | Old Irish |
—
|
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: Old Irish | Statement: [Fortriu, sourceLanguageOfName, Old Irish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceLanguageOfName Context triple: [Fortriu, sourceLanguageOfName, Old Irish]
-
A.
originalNameLanguage
chosen
Indicates that the specified language is the language in which an entity’s original or primary name was expressed.
-
B.
languageOfNamesake
Indicates the language in which the namesake of an entity (such as a person, place, or object) is named or expressed.
-
C.
sourceLanguageRegion
Indicates the geographic or cultural region associated with the language from which something originates or is derived.
-
D.
nativeLanguageFamilyName
Indicates the name of the language family to which an entity’s native language belongs.
-
E.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by another entity.
- 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_69eeb31fbd888190a82dac5822e453bc |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a19604881908083cbc5e4e38559 |
completed | May 2, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 4:24 a.m.