Triple
T2950663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Šušnjevica |
E79811
|
entity |
| Predicate | minorityLanguageSpoken |
P30213
|
FINISHED |
| Object | Istro-Romanian |
E16631
|
NE FINISHED |
How this triple was built (3 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: Istro-Romanian | Statement: [Šušnjevica, minorityLanguageSpoken, Istro-Romanian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Istro-Romanian Context triple: [Šušnjevica, minorityLanguageSpoken, Istro-Romanian]
-
A.
Istro-Romanian
chosen
Istro-Romanian is an endangered Eastern Romance language variety spoken by a small community in the Istrian Peninsula, primarily in Croatia.
-
B.
Megleno-Romanian
Megleno-Romanian is an Eastern Romance language variety spoken by a small ethnic community in the Meglen region, primarily in Greece and North Macedonia.
-
C.
Aromanian
Aromanian is an Eastern Romance language spoken by the Aromanian people in the Balkans, closely related to Romanian but distinct in its history, vocabulary, and phonology.
-
D.
Dacian language
The Dacian language was an extinct Indo-European tongue once spoken by the ancient Dacian people in the region that is now primarily Romania and surrounding areas.
-
E.
Balkan Latin
Balkan Latin is the hypothesized regional variety of Vulgar Latin once spoken in the Balkans, from which the Eastern Romance languages, including Aromanian, are believed to have evolved.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minorityLanguageSpoken Context triple: [Šušnjevica, minorityLanguageSpoken, Istro-Romanian]
-
A.
majorityLanguageOf
Indicates that a given language is the primary or most widely spoken language within a specified group, region, or entity.
-
B.
ethnicLanguageStatus
Indicates the status or role of a language in relation to a particular ethnic group (e.g., primary, secondary, heritage, or minority language).
-
C.
isOfficialMinorityLanguageIn
Indicates that a language has formal, legally recognized minority-language status within a specified political or geographic entity.
-
D.
minorityLanguagePolicy
Indicates a policy or set of rules governing the recognition, protection, and use of languages spoken by minority groups within a larger political or social context.
-
E.
isSpokenByMinority
chosen
Indicates that the language or dialect is used primarily by a numerically smaller or less dominant group within a larger population.
- F. None of above.
Provenance (4 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_69ad8b1276588190a374a0b12e0f7bdf |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad98fbb7d4819081c241f3ff9165e5 |
completed | March 8, 2026, 3:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b12e1d59a48190b06ebe298590feb8 |
completed | March 11, 2026, 8:55 a.m. |
| PD | Predicate disambiguation | batch_69ad960a70ac8190816b5ae3e8631031 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:57 p.m.