Triple
T15942619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lahnda |
E386602
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Jatki |
E77871
|
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: Jatki | Statement: [Lahnda, hasDialect, Jatki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jatki Context triple: [Lahnda, hasDialect, Jatki]
-
A.
Jatki
chosen
Jatki is a regional dialect of the Saraiki language spoken primarily in parts of Pakistan.
-
B.
Juketau
Juketau was a notable medieval settlement within the historical region of Volga Bulgaria, likely serving as a local center of trade or administration.
-
C.
Jaugada
Jaugada is an ancient fortified settlement in present-day Odisha, India, best known for its Mauryan-era remains and an important rock edict of Emperor Ashoka.
-
D.
Ojakkala
Ojakkala is a village in the municipality of Vihti in southern Finland, known for its rural residential character and proximity to the Helsinki metropolitan area.
-
E.
Partakko
Partakko is a small village in the municipality of Inari in northern Finnish Lapland.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156cefe948190af40eac92983edbc |
completed | April 16, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe7455c48190bfad24eb8905426d |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:53 a.m.