Triple
T1990056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thaana script |
E43230
|
entity |
| Predicate | hasVowelSignsCount |
P4430
|
FINISHED |
| Object | 11 vowel diacritics (approximate standard set) |
—
|
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: 11 vowel diacritics (approximate standard set) | Statement: [Thaana script, hasVowelSignsCount, 11 vowel diacritics (approximate standard set)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVowelSignsCount Context triple: [Thaana script, hasVowelSignsCount, 11 vowel diacritics (approximate standard set)]
-
A.
hasNumberOfVowelLetters
chosen
Indicates that an entity is associated with a specific count of vowel letters it contains.
-
B.
hasConsonantSigns
Indicates that one entity possesses or includes consonant sign characters as part of its representation or structure.
-
C.
hasVowelFeature
Indicates that an entity possesses a specific vowel-related phonological or articulatory feature.
-
D.
hasDistinctVowelLetters
Indicates that the subject contains vowel letters that are all different from one another, with no vowel repeated.
-
E.
containsVowelLetters
Indicates that the subject includes one or more vowel letters within its sequence of characters.
- 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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.