Triple
T9595529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tats |
E231520
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Southern Tat |
E261676
|
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: Southern Tat | Statement: [Tats, hasDialect, Southern Tat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southern Tat Context triple: [Tats, hasDialect, Southern Tat]
-
A.
Southern Tat
chosen
Southern Tat is a regional variety of the Tat language spoken by Tat communities in parts of the South Caucasus.
-
B.
Southern Lau
Southern Lau is a dialectal variety of the Lau language spoken on Malaita in the Solomon Islands.
-
C.
South-East Region
The South-East Region is an administrative and statistical region of Ireland encompassing several counties in the southeast of the country, known for its mix of historic cities, agriculture, and coastal areas.
-
D.
South East
South East is one of Nigeria’s six geopolitical zones, predominantly inhabited by Igbo-speaking people and known for its dense population, commerce, and vibrant cultural heritage.
-
E.
South West
South West is a London Assembly constituency covering parts of southwest London, including boroughs such as Hounslow, Richmond upon Thames, and Kingston upon Thames.
- 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_69ca8482884481908eccdfdf64d6fbf7 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a164c20819093fa863f8f5f79c0 |
completed | April 1, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d16199845881908f8a91182ca48250 |
completed | April 4, 2026, 7:08 p.m. |
Created at: March 30, 2026, 8:07 p.m.