Triple
T16951279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Mam |
E411184
|
entity |
| Predicate | hasDialectContinuumWith |
P18451
|
FINISHED |
| Object | Northern Mam |
E411183
|
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: Northern Mam | Statement: [Southern Mam, hasDialectContinuumWith, Northern Mam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Northern Mam Context triple: [Southern Mam, hasDialectContinuumWith, Northern Mam]
-
A.
Northern Mam
chosen
Northern Mam is a Mayan language variety spoken primarily in the highland regions of Guatemala by Mam indigenous communities.
-
B.
Northern Anii
Northern Anii is a regional variety of the Anii language spoken by communities in the northern part of the Anii-speaking area of West Africa.
-
C.
March North
March North is an electoral ward in the town of March, Cambridgeshire, represented on the local council.
-
D.
Northern Uma
Northern Uma is a regional dialect of the Uma language spoken by communities in Central Sulawesi, Indonesia.
-
E.
Northern Dimlî
Northern Dimlî is a regional variety of the Dimlî (Zaza) language spoken primarily in the northern parts of its traditional area in eastern Turkey.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfb6e5fc8190b1bd3ad1c2773685 |
completed | April 18, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d46213b08190b33b48d12bc795d1 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.