Triple
T22019721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahmad Nizam Shah I |
E543808
|
entity |
| Predicate | languageOfCourt |
P4185
|
FINISHED |
| Object | Dakhni |
—
|
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: Dakhni | Statement: [Ahmad Nizam Shah I, languageOfCourt, Dakhni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dakhni Context triple: [Ahmad Nizam Shah I, languageOfCourt, Dakhni]
-
A.
Dakhni
chosen
Dakhni is a historical Indo-Aryan language variety that developed in the Deccan region of India, blending early Urdu/Hindavi with local languages and Persian-Arabic influences.
-
B.
Kutchi
Kutchi is an Indo-Aryan language spoken primarily by the Kutchi people of the Kutch region in the Indian state of Gujarat and in diaspora communities abroad.
-
C.
Awadhi
Awadhi is an Indo-Aryan language of northern India, traditionally spoken in parts of Uttar Pradesh and surrounding regions and known for its rich literary and folk traditions.
-
D.
Dhuleti
Dhuleti is the vibrant second day of the Hindu festival of Holi, celebrated with the playful throwing of colored powders and water.
-
E.
Gujora
Gujora is a coastal village on Geoje Island in South Korea, known for its beaches and seaside tourism.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c6b5fc8190bc49ddb058f28a44 |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:23 p.m.