Triple
T23094362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuki-Chin group |
E575842
|
entity |
| Predicate | hasMemberLanguage |
P7390
|
FINISHED |
| Object | Mara language |
—
|
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: Mara language | Statement: [Kuki-Chin group, hasMemberLanguage, Mara language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mara language Context triple: [Kuki-Chin group, hasMemberLanguage, Mara language]
-
A.
Mara language
chosen
The Mara language is a Kuki-Chin language spoken primarily by the Mara people in parts of northeastern India and western Myanmar.
-
B.
Marsela language
The Marsela language is an Austronesian language spoken on Marsela Island in the Maluku province of Indonesia.
-
C.
Maru language
The Maru language is a Sino-Tibetan language spoken primarily by the Maru (Lawngwaw) people in parts of Myanmar and neighboring regions.
-
D.
Mararit language
The Mararit language is a lesser-known Nilo-Saharan language spoken by the Mararit people in parts of Chad and Sudan.
-
E.
Marda language
The Marda language is a lesser-known Nilo-Saharan language variety spoken by the Kunama people in parts of the Horn of Africa.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de2ed088190971ff08c58b15aad |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:57 p.m.