Triple
T20753896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bumiputera |
E510799
|
entity |
| Predicate | includesEthnicGroup |
P1898
|
FINISHED |
| Object | Minangkabau Malaysians |
—
|
NE NERFINISHED |
How this triple was built (3 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: Minangkabau Malaysians | Statement: [Bumiputera, includesEthnicGroup, Minangkabau Malaysians]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Minangkabau Malaysians Context triple: [Bumiputera, includesEthnicGroup, Minangkabau Malaysians]
-
A.
Indian Malays
Indian Malays are an ethnic community in India descended largely from Malay and other Southeast Asian Muslims who settled in the subcontinent through historical maritime trade and migration.
-
B.
Peranakan Malay
Peranakan Malay is a creole Malay variety historically spoken by the Peranakan Chinese community, characterized by a strong blend of Malay and Southern Chinese (especially Hokkien) linguistic and cultural elements.
-
C.
Bumiputera
Bumiputera is a Malaysian legal and socio-political category that grants certain indigenous and Malay-heritage groups, including many Javanese Malaysians, preferential rights and affirmative action benefits.
-
D.
Malay peoples
The Malay peoples are a diverse group of closely related Austronesian ethnic communities native to the Malay Peninsula, eastern Sumatra, coastal Borneo, and surrounding regions of Southeast Asia, sharing similar languages, cultures, and Islamic heritage.
-
E.
Kadazan-Dusun
Kadazan-Dusun are an indigenous ethnic group of Sabah, Malaysia, known for their distinct language, rice-farming traditions, and cultural festivals such as Kaamatan.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Minangkabau Malaysians Target entity description: Minangkabau Malaysians are a Malay-speaking ethnic community in Malaysia of Minangkabau origin, known for their matrilineal culture and strong historical ties to West Sumatra, Indonesia.
-
A.
Indian Malays
Indian Malays are an ethnic community in India descended largely from Malay and other Southeast Asian Muslims who settled in the subcontinent through historical maritime trade and migration.
-
B.
Peranakan Malay
Peranakan Malay is a creole Malay variety historically spoken by the Peranakan Chinese community, characterized by a strong blend of Malay and Southern Chinese (especially Hokkien) linguistic and cultural elements.
-
C.
Bumiputera
Bumiputera is a Malaysian legal and socio-political category that grants certain indigenous and Malay-heritage groups, including many Javanese Malaysians, preferential rights and affirmative action benefits.
-
D.
Malay peoples
chosen
The Malay peoples are a diverse group of closely related Austronesian ethnic communities native to the Malay Peninsula, eastern Sumatra, coastal Borneo, and surrounding regions of Southeast Asia, sharing similar languages, cultures, and Islamic heritage.
-
E.
Kadazan-Dusun
Kadazan-Dusun are an indigenous ethnic group of Sabah, Malaysia, known for their distinct language, rice-farming traditions, and cultural festivals such as Kaamatan.
- F. None of above.
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_69e0b4c909ec8190b05987f1639513f6 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c22d0ebc8190b17077326f540f98 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:34 p.m.