Triple
T8518455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mundari |
E201634
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Santali |
E38852
|
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: Santali | Statement: [Mundari, closelyRelatedTo, Santali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Santali Context triple: [Mundari, closelyRelatedTo, Santali]
-
A.
Santhali
chosen
Santhali is an Austroasiatic language spoken primarily by the Santal people in eastern India, Bangladesh, Nepal, and Bhutan.
-
B.
Nagpuri
Nagpuri is an Indo-Aryan language spoken primarily in parts of eastern India, especially in and around the present-day state of Jharkhand.
-
C.
Kurukh
Kurukh is an indigenous Dravidian language spoken primarily by the Oraon tribal communities in eastern and central India.
-
D.
Bhojpuri
Bhojpuri is an Indo-Aryan language spoken primarily in eastern Uttar Pradesh, western Bihar, and parts of Nepal, with a rich folk culture and a large diaspora community.
-
E.
Mundari
Mundari is an Austroasiatic Munda language of eastern India, spoken primarily by the Munda people in states such as Jharkhand, Odisha, and West Bengal.
- 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe626787c819087e72dd76b2d9310 |
completed | March 31, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebb6855ec8190a85e5afeb656ee7d |
completed | April 2, 2026, 6:54 p.m. |
Created at: March 30, 2026, 6:16 p.m.