Triple
T5985709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | indigenous peoples of Taiwan |
E133219
|
entity |
| Predicate | recognizedGroup |
P310
|
FINISHED |
| Object |
Hla’alua
Hla’alua are a small indigenous ethnic group of Taiwan with their own distinct language, culture, and traditions, officially recognized by the Taiwanese government.
|
E560018
|
NE FINISHED |
How this triple was built (4 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: Hla’alua | Statement: [indigenous peoples of Taiwan, recognizedGroup, Hla’alua]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hla’alua Context triple: [indigenous peoples of Taiwan, recognizedGroup, Hla’alua]
-
A.
Lauliʻi
Lauliʻi is a coastal village in the Eastern District of American Samoa known for its traditional Samoan community and scenic island setting.
-
B.
Ilala
Ilala is a central administrative district of Dar es Salaam in Tanzania, encompassing key commercial, residential, and transport hubs of the city.
-
C.
Aluta
Aluta is the historical name of the Olt River, a major waterway flowing through central Romania.
-
D.
Mlahsô
Mlahsô is an endangered Neo-Aramaic language historically spoken by Assyrian/Syriac communities in parts of southeastern Turkey and northeastern Syria.
-
E.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hla’alua Triple: [indigenous peoples of Taiwan, recognizedGroup, Hla’alua]
Generated description
Hla’alua are a small indigenous ethnic group of Taiwan with their own distinct language, culture, and traditions, officially recognized by the Taiwanese government.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hla’alua Target entity description: Hla’alua are a small indigenous ethnic group of Taiwan with their own distinct language, culture, and traditions, officially recognized by the Taiwanese government.
-
A.
Lauliʻi
Lauliʻi is a coastal village in the Eastern District of American Samoa known for its traditional Samoan community and scenic island setting.
-
B.
Ilala
Ilala is a central administrative district of Dar es Salaam in Tanzania, encompassing key commercial, residential, and transport hubs of the city.
-
C.
Aluta
Aluta is the historical name of the Olt River, a major waterway flowing through central Romania.
-
D.
Mlahsô
Mlahsô is an endangered Neo-Aramaic language historically spoken by Assyrian/Syriac communities in parts of southeastern Turkey and northeastern Syria.
-
E.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
- F. None of above. chosen
Provenance (5 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_69c0087010d081908bb8142342d63330 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0560bae148190ad4755defaaf471b |
completed | March 22, 2026, 8:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0e42a0fcc8190ab8d7f797b58a8e0 |
completed | March 23, 2026, 6:56 a.m. |
| NEDg | Description generation | batch_69c0f6e214748190a8e9452353853da4 |
completed | March 23, 2026, 8:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0f74c175c81909d4414ca34fa85dd |
completed | March 23, 2026, 8:18 a.m. |
Created at: March 22, 2026, 4:04 p.m.