Triple
T36712938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LR ĀM |
E906840
|
entity |
| Predicate | fullNameInLatvian |
P26844
|
FINISHED |
| Object | Latvijas Republikas Ārlietu ministrija |
—
|
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: Latvijas Republikas Ārlietu ministrija | Statement: [LR ĀM, fullNameInLatvian, Latvijas Republikas Ārlietu ministrija]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fullNameInLatvian Context triple: [LR ĀM, fullNameInLatvian, Latvijas Republikas Ārlietu ministrija]
-
A.
nameInLatvian
chosen
Indicates that an entity is referred to by a specific name when expressed in the Latvian language.
-
B.
nameInLithuanian
Indicates that one entity is the Lithuanian-language name or label for another entity.
-
C.
nameFormInLatin
Indicates that an entity’s name is expressed or recorded in its Latin-language form.
-
D.
nameInLatinAlphabet
Indicates that an entity’s name is written or represented using the Latin alphabet.
-
E.
nameDayInLatvia
Indicates that a person’s name corresponds to a specific name day in the Latvian name day calendar.
- 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c8161dfc8190890b03483f8524c1 |
completed | May 3, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.