Triple
T1322769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Sulawesi languages |
E28256
|
entity |
| Predicate | hasSubgroup |
P747
|
FINISHED |
| Object |
Mandar language
Mandar is an Austronesian language spoken primarily by the Mandar people along the western coast of Sulawesi in Indonesia.
|
E152161
|
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: Mandar language | Statement: [South Sulawesi languages, hasSubgroup, Mandar language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mandar language Context triple: [South Sulawesi languages, hasSubgroup, Mandar language]
-
A.
Maban languages
Maban languages are a small group of closely related Nilo-Saharan languages spoken primarily in eastern Chad and western Sudan.
-
B.
Fala language
Fala is a small Ibero-Romance language spoken in a few villages in Spain’s Extremadura region, notable for its close relation to Galician-Portuguese and its strong local identity.
-
C.
Gondi language
The Gondi language is a Dravidian language spoken by the indigenous Gond people of central India, written in multiple scripts including Telugu and Devanagari.
-
D.
Lambadi language
The Lambadi language is an Indo-Aryan language spoken primarily by the Banjara (Lambadi) community in parts of India.
-
E.
Kavalan language
The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
- 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: Mandar language Triple: [South Sulawesi languages, hasSubgroup, Mandar language]
Generated description
Mandar is an Austronesian language spoken primarily by the Mandar people along the western coast of Sulawesi in Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mandar language Target entity description: Mandar is an Austronesian language spoken primarily by the Mandar people along the western coast of Sulawesi in Indonesia.
-
A.
Maban languages
Maban languages are a small group of closely related Nilo-Saharan languages spoken primarily in eastern Chad and western Sudan.
-
B.
Fala language
Fala is a small Ibero-Romance language spoken in a few villages in Spain’s Extremadura region, notable for its close relation to Galician-Portuguese and its strong local identity.
-
C.
Gondi language
The Gondi language is a Dravidian language spoken by the indigenous Gond people of central India, written in multiple scripts including Telugu and Devanagari.
-
D.
Lambadi language
The Lambadi language is an Indo-Aryan language spoken primarily by the Banjara (Lambadi) community in parts of India.
-
E.
Kavalan language
The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
- 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19b76b48190aa8857b80971a842 |
completed | March 1, 2026, 10:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acbf2e13dc8190902879be5fa69adb |
completed | March 8, 2026, 12:13 a.m. |
| NEDg | Description generation | batch_69acbf94e6e881908d15b2ef99f17668 |
completed | March 8, 2026, 12:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acc0b212608190bbb2310402d86ed9 |
completed | March 8, 2026, 12:20 a.m. |
Created at: March 1, 2026, 7:55 p.m.