Triple
T5269453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nabaneeta |
E119219
|
entity |
| Predicate | writingSystem |
P454
|
FINISHED |
| Object | Bengali script |
E25965
|
NE 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: Bengali script | Statement: [Nabaneeta, writingSystem, Bengali script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bengali script Context triple: [Nabaneeta, writingSystem, Bengali script]
-
A.
Bengali script
chosen
Bengali script is an abugida used across eastern South Asia to write languages such as Bengali and Assamese, derived from the ancient Brahmi script.
-
B.
Odia script
Odia script is an abugida of the Brahmic family used primarily to write the Odia language and several other regional Indo-Aryan languages of eastern India.
-
C.
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.
-
D.
Devanagari script
Devanagari script is an abugida writing system used for several major South Asian languages, including Hindi, Marathi, Nepali, and Sanskrit.
-
E.
Nandinagari script
Nandinagari script is a historical Brahmic script of southern India, primarily used to write Sanskrit and related languages in the Deccan region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd446c38e081908cdaf113bdf86790 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7bfdc9bc81908307f44f32fe9338 |
completed | March 20, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69befe9542488190b715bc4bd800cb02 |
completed | March 21, 2026, 8:24 p.m. |
Created at: March 20, 2026, 1:51 p.m.