Triple
T13846433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hron River |
E332816
|
entity |
| Predicate | nameVariantLanguage |
P63334
|
FINISHED |
| Object | Hungarian |
—
|
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: Hungarian | Statement: [Hron River, nameVariantLanguage, Hungarian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nameVariantLanguage Context triple: [Hron River, nameVariantLanguage, Hungarian]
-
A.
alternateLanguageName
chosen
Indicates that an entity has an additional name or label in a different language from its primary or default name.
-
B.
linguisticVariant
Indicates that one linguistic form is an alternative version or expression of another within the same or closely related language context.
-
C.
languageVariant
Indicates that one language is a variant, dialect, or localized form of another language.
-
D.
officialLanguageVariant
Indicates that one language variety is an officially recognized form or version of another language within a specific jurisdiction or context.
-
E.
hasEthnonymVariant
Indicates that one ethnonym is an alternative or variant form of another ethnonym referring to the same ethnic group.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02b1a25c8190a9f85ba43c421188 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.