Triple
T1734585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konkani |
E37892
|
entity |
| Predicate | hasDialects |
P4251
|
FINISHED |
| Object | Salcete Konkani |
E37892
|
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: Salcete Konkani | Statement: [Konkani, hasDialects, Salcete Konkani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salcete Konkani Context triple: [Konkani, hasDialects, Salcete Konkani]
-
A.
Konkani
chosen
Konkani is an Indo-Aryan language spoken primarily along India’s Konkan coast, especially in Goa and parts of Karnataka and Maharashtra.
-
B.
Tulu
Tulu is a Dravidian language spoken primarily in the coastal regions of Karnataka and northern Kerala in southwestern India, known for its rich oral traditions and distinct cultural identity.
-
C.
Kurukh
Kurukh is an indigenous Dravidian language spoken primarily by the Oraon tribal communities in eastern and central India.
-
D.
Haketia
Haketia is a Judeo-Spanish dialect historically spoken by Sephardic Jews in northern Morocco and parts of Gibraltar, characterized by strong influences from Moroccan Arabic and Hebrew.
-
E.
Kolami
Kolami is a Dravidian language spoken primarily by the Kolam tribal communities in central India, especially in parts of Maharashtra and Telangana.
- 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_69a8861cc6ac8190ac0b2e31ccf62851 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa63a2168c819093d302632ff4b7c2 |
completed | March 6, 2026, 5:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adbf498848819085cd7faffd86cd77 |
completed | March 8, 2026, 6:26 p.m. |
Created at: March 4, 2026, 7:30 p.m.