Triple
T22303073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumatran languages |
E551304
|
entity |
| Predicate | includeLanguage |
P2177
|
FINISHED |
| Object |
Serawai
Serawai is an Austronesian language spoken by the Serawai people in southwestern Sumatra, Indonesia.
|
E1529582
|
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: Serawai | Statement: [Sumatran languages, includeLanguage, Serawai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Serawai Context triple: [Sumatran languages, includeLanguage, Serawai]
-
A.
Tagakaulo
Tagakaulo are an indigenous ethnic group in the southern Philippines, traditionally inhabiting parts of Mindanao and known for their distinct language and cultural practices.
-
B.
Djali
Djali is the clever pet goat of Esmeralda in Victor Hugo’s novel "The Hunchback of Notre-Dame," known for performing tricks and playing a key role in the story.
-
C.
Kongorong
Kongorong is a small rural locality in South Australia's Limestone Coast region, known for its farming community and proximity to coastal attractions.
-
D.
Djoeka
Djoeka, also known as Njuká, is a Maroon ethnic group in Suriname and French Guiana descended from escaped African slaves who established independent communities in the rainforest.
-
E.
Warrau
Warrau is an indigenous language spoken by the Warao people of the Orinoco Delta region in Venezuela and neighboring areas.
- 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: Serawai Triple: [Sumatran languages, includeLanguage, Serawai]
Generated description
Serawai is an Austronesian language spoken by the Serawai people in southwestern Sumatra, Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Serawai Target entity description: Serawai is an Austronesian language spoken by the Serawai people in southwestern Sumatra, Indonesia.
-
A.
Tagakaulo
Tagakaulo are an indigenous ethnic group in the southern Philippines, traditionally inhabiting parts of Mindanao and known for their distinct language and cultural practices.
-
B.
Djali
Djali is the clever pet goat of Esmeralda in Victor Hugo’s novel "The Hunchback of Notre-Dame," known for performing tricks and playing a key role in the story.
-
C.
Kongorong
Kongorong is a small rural locality in South Australia's Limestone Coast region, known for its farming community and proximity to coastal attractions.
-
D.
Djoeka
Djoeka, also known as Njuká, is a Maroon ethnic group in Suriname and French Guiana descended from escaped African slaves who established independent communities in the rainforest.
-
E.
Warrau
Warrau is an indigenous language spoken by the Warao people of the Orinoco Delta region in Venezuela and neighboring areas.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1572517588190bef6f8bfb76afb19 |
completed | April 29, 2026, 12:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0acc9cd4508190825732ffc8b9fa84 |
completed | May 18, 2026, 8:23 a.m. |
| NEDg | Description generation | batch_6a0acd8b04d88190a545cec751e4a635 |
completed | May 18, 2026, 8:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ace5e9b948190bd4fb7092e6fb62e |
completed | May 18, 2026, 8:31 a.m. |
Created at: April 16, 2026, 8:41 p.m.