Triple
T21868915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Braille |
E539952
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Hindi Braille |
—
|
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: Hindi Braille | Statement: [Braille, hasVariant, Hindi Braille]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hindi Braille Context triple: [Braille, hasVariant, Hindi Braille]
-
A.
Braille
chosen
Braille is a tactile writing system using raised dots that enables blind and visually impaired people to read and write through touch.
-
B.
Devanagari script
Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
-
C.
Korean Braille
Korean Braille is the tactile writing system for the Korean language, designed to represent Hangul syllables in a format readable by touch for blind and visually impaired users.
-
D.
Ol Chiki script
Ol Chiki script is an alphabetic writing system specifically created in the 20th century for the Santhali language, used primarily by the Santal people of eastern India and neighboring regions.
-
E.
Akshara Nagari
Akshara Nagari is a popular moniker for Kottayam, a Kerala town renowned for its high literacy, rich publishing tradition, and educational institutions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f33305d081908cd070134420607a |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 6:57 p.m.