Triple
T6134710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Icelandic branch of the House of Glücksburg |
E136803
|
entity |
| Predicate | languageOfRealm |
P50752
|
FINISHED |
| Object | Icelandic |
—
|
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: Icelandic | Statement: [Icelandic branch of the House of Glücksburg, languageOfRealm, Icelandic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfRealm Context triple: [Icelandic branch of the House of Glücksburg, languageOfRealm, Icelandic]
-
A.
languageOfFictionalUniverse
Indicates the language used or spoken within a fictional universe or setting.
-
B.
regionLanguage
Indicates that a particular language is used or officially recognized within a specific geographic region.
-
C.
languageOfRulers
Indicates the language predominantly used or officially adopted by a group of rulers in governing or representing their domain.
-
D.
standardLanguageOf
Indicates that one entity serves as the officially recognized or commonly used standard language for another entity (such as a country, region, or organization).
-
E.
governingLanguage
chosen
Indicates the language that holds official or authoritative status over a given entity, such as a region, organization, or document.
- 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_69c008a179388190a3b5a081bbf46d55 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05c7f34d081909e589b201b22be21 |
completed | March 22, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c055f19b0c81908be34a00ab218723 |
completed | March 22, 2026, 8:49 p.m. |
Created at: March 22, 2026, 4:15 p.m.