Triple
T23855877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tahitian alphabet |
E592307
|
entity |
| Predicate | diacriticFunction |
P154209
|
FINISHED |
| Object | mark vowel length |
—
|
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: mark vowel length | Statement: [Tahitian alphabet, diacriticFunction, mark vowel length]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diacriticFunction Context triple: [Tahitian alphabet, diacriticFunction, mark vowel length]
-
A.
diacriticType
Indicates the specific kind or category of diacritic mark associated with a character or symbol.
-
B.
diacriticForms
Indicates that one written form is a diacritic variant or includes diacritic marks relative to another form.
-
C.
usesDiacritics
Indicates that the referenced text or linguistic element employs diacritical marks as part of its written form.
-
D.
usesDiacriticsFrom
Indicates that one entity employs or incorporates the diacritical marks that originate from or are characteristic of another entity.
-
E.
diacriticStrippedForm
Indicates that one textual form is derived from another by removing all diacritic marks (such as accents or umlauts) from its characters.
- F. None of above. chosen
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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c98b29a881909eb60c1be1acdbe9 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f16e348b548190b76e50f9b611f76d |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 8:12 p.m.