Triple
T26077068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latvian alphabet |
E657715
|
entity |
| Predicate | hasDiacriticType |
P18659
|
FINISHED |
| Object | macron |
—
|
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: macron | Statement: [Latvian alphabet, hasDiacriticType, macron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDiacriticType Context triple: [Latvian alphabet, hasDiacriticType, macron]
-
A.
diacriticType
chosen
Indicates the specific kind or category of diacritic mark associated with a character or symbol.
-
B.
usesDiacritics
Indicates that the referenced text or linguistic element employs diacritical marks as part of its written form.
-
C.
diacriticFunction
Indicates that a diacritic serves a particular role or effect in relation to the base character or linguistic unit it modifies.
-
D.
usesDiacriticsFrom
Indicates that one entity employs or incorporates the diacritical marks that originate from or are characteristic of another entity.
-
E.
hasSpellingWithAccent
Indicates that one form of a word or name is spelled using accented characters compared to another form.
- 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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 26, 2026, 7:35 p.m.