Triple
T6510081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamuju language |
E150104
|
entity |
| Predicate | isRelatedTo |
P37
|
FINISHED |
| Object | Bugis language |
E128374
|
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: Bugis language | Statement: [Mamuju language, isRelatedTo, Bugis language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bugis language Context triple: [Mamuju language, isRelatedTo, Bugis language]
-
A.
Buginese language
chosen
Buginese language is an Austronesian language spoken primarily by the Bugis people of South Sulawesi, Indonesia, known for its traditional Lontara script and rich literary heritage.
-
B.
Kayabí language
The Kayabí language is an indigenous Tupian language spoken by the Kayabí people of Brazil, known for its role in preserving their cultural and linguistic heritage.
-
C.
Bugotu language
The Bugotu language is an Oceanic language spoken by the Bugotu people of Santa Isabel Island in the Solomon Islands.
-
D.
Sawunese language
The Sawunese language is an Austronesian language spoken primarily on Savu (Sawu) Island in eastern Indonesia.
-
E.
Yaeyama language
The Yaeyama language is a Southern Ryukyuan language spoken in Japan’s Yaeyama Islands, distinct from standard Japanese and recognized as endangered.
- 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_69c687ef291081909d437f035eef1cda |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c69f398f10819096342f3646cefcc2 |
completed | March 27, 2026, 3:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6cb5782fc8190a56b714bbc007490 |
completed | March 27, 2026, 6:24 p.m. |
Created at: March 27, 2026, 1:43 p.m.