Triple
T5092826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikelis |
E114792
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Latvian |
E168863
|
NE 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: Latvian | Statement: [Mikelis, hasLanguage, Latvian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Latvian Context triple: [Mikelis, hasLanguage, Latvian]
-
A.
Latvian
chosen
Latvian is a Baltic language spoken primarily in Latvia and one of the official languages of the European Union.
-
B.
Latvians
Latvians are a Baltic ethnic group native to Latvia, known for their distinct Latvian language, rich folk traditions, and cultural heritage along the eastern coast of the Baltic Sea.
-
C.
Latn
Latn is the ISO 15924 script code representing the Latin alphabet used for writing numerous modern languages worldwide.
-
D.
Lithuanian
Lithuanian is a Baltic language spoken primarily in Lithuania and known for preserving many archaic features of Proto-Indo-European.
-
E.
Livonian language
The Livonian language is an almost extinct Uralic language historically spoken by the Livonian people along the northern coast of Latvia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd754369708190bf4e171a904a19e1 |
completed | March 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beb14f097081908d835190f13796dd |
completed | March 21, 2026, 2:55 p.m. |
Created at: March 20, 2026, 1:40 p.m.