Triple
T20834463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comorian language |
E512921
|
entity |
| Predicate | hasVariety |
P455
|
FINISHED |
| Object |
Shingazidja
Shingazidja is a Bantu language variety spoken primarily on Grande Comore in the Comoros archipelago.
|
E1451998
|
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: Shingazidja | Statement: [Comorian language, hasVariety, Shingazidja]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shingazidja Context triple: [Comorian language, hasVariety, Shingazidja]
-
A.
Uma Mbatangu
Uma Mbatangu is a traditional Sumbanese house type characterized by its tall peaked thatched roof and elevated wooden structure, commonly found in the Waikabubak area of Indonesia.
-
B.
Issoze-Ngondet
Issoze-Ngondet is the surname of Emmanuel Issoze-Ngondet, a Gabonese politician who served as Prime Minister of Gabon.
-
C.
Mbula-Bwazza
Mbula-Bwazza is a Jarawan Bantu language spoken in parts of Nigeria, known for its place within the wider Bantu-related language continuum of West Africa.
-
D.
Zing Mumuye
Zing Mumuye is a regional dialect of the Mumuye language spoken by communities in and around the Zing area of Nigeria.
-
E.
Uria Simango
Uria Simango was a Mozambican Presbyterian pastor and nationalist politician who became a prominent early leader in the country’s independence movement.
- 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: Shingazidja Triple: [Comorian language, hasVariety, Shingazidja]
Generated description
Shingazidja is a Bantu language variety spoken primarily on Grande Comore in the Comoros archipelago.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Shingazidja Target entity description: Shingazidja is a Bantu language variety spoken primarily on Grande Comore in the Comoros archipelago.
-
A.
Uma Mbatangu
Uma Mbatangu is a traditional Sumbanese house type characterized by its tall peaked thatched roof and elevated wooden structure, commonly found in the Waikabubak area of Indonesia.
-
B.
Issoze-Ngondet
Issoze-Ngondet is the surname of Emmanuel Issoze-Ngondet, a Gabonese politician who served as Prime Minister of Gabon.
-
C.
Mbula-Bwazza
Mbula-Bwazza is a Jarawan Bantu language spoken in parts of Nigeria, known for its place within the wider Bantu-related language continuum of West Africa.
-
D.
Zing Mumuye
Zing Mumuye is a regional dialect of the Mumuye language spoken by communities in and around the Zing area of Nigeria.
-
E.
Uria Simango
Uria Simango was a Mozambican Presbyterian pastor and nationalist politician who became a prominent early leader in the country’s independence movement.
- 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_69e0b4cf62a88190bbf92351e9e57259 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c32554648190bd66ac99b3a9072b |
completed | April 21, 2026, 12:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a090084a1c481909a344ee40d846b10 |
completed | May 16, 2026, 11:40 p.m. |
| NEDg | Description generation | batch_6a0900fd590c8190b42faa5c5191189a |
completed | May 16, 2026, 11:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0901950c1c8190befa72dc20236b9e |
completed | May 16, 2026, 11:45 p.m. |
Created at: April 16, 2026, 12:42 p.m.