Triple
T19369958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sain Tathan |
E484506
|
entity |
| Predicate | hasWelshName |
P4705
|
FINISHED |
| Object | Sain Tathan |
—
|
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: Sain Tathan | Statement: [Sain Tathan, hasWelshName, Sain Tathan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sain Tathan Context triple: [Sain Tathan, hasWelshName, Sain Tathan]
-
A.
Sain Tathan
chosen
Sain Tathan is the Welsh name for the village of St Athan in the Vale of Glamorgan, Wales.
-
B.
Saklatvala
Saklatvala is an Indian-origin surname most notably associated with Shapurji Saklatvala, a pioneering communist and one of the first British MPs of Indian descent.
-
C.
Lotha Naga
Lotha Naga are an indigenous Naga ethnic community of north-eastern India known for their distinct language, rich folk traditions, and vibrant festivals such as Tokhu Emong.
-
D.
Sotang Rai
Sotang Rai are a subgroup of the Rai people of eastern Nepal, known for their distinct Kirati language, culture, and traditions.
-
E.
Mor Thiam
Mor Thiam is a Senegalese master drummer, cultural historian, and educator known for his influential role in promoting West African music and for being the father of singer Akon.
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e619af33e481908643f8beb2f498dc |
completed | April 20, 2026, 12:18 p.m. |
Created at: April 10, 2026, 1:35 p.m.