Triple
T1890718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seraiki |
E41867
|
entity |
| Predicate | hasDialects |
P4251
|
FINISHED |
| Object | Derawali |
E80367
|
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: Derawali | Statement: [Seraiki, hasDialects, Derawali]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derawali Context triple: [Seraiki, hasDialects, Derawali]
-
A.
Derawali
chosen
Derawali is a regional dialect of the Saraiki language spoken primarily in and around the Dera Ghazi Khan and Dera Ismail Khan areas of Pakistan.
-
B.
Mewati
Mewati is an Indo-Aryan language variety spoken primarily in the Mewat region of northwestern India, associated with the Meo community.
-
C.
Pulaar
Pulaar is a Fula language variety spoken primarily by the Fula (Fulani) people across West Africa, including in Mauritania, Senegal, and neighboring countries.
-
D.
Gaur
Gaur is a ruined medieval city on the India–Bangladesh border, historically a major capital of Bengal known for its Islamic architecture and archaeological remains.
-
E.
Nandi
Nandi is the sacred bull and devoted gatekeeper of the Hindu god Shiva, revered as a symbol of strength, righteousness, and dharma.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb14475448190b291ada3454bf98b |
completed | March 7, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adeae81e4c8190bf480215a8a33630 |
completed | March 8, 2026, 9:32 p.m. |
Created at: March 4, 2026, 7:34 p.m.