Triple
T6771587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siwu language |
E155055
|
entity |
| Predicate | hasDialects |
P4251
|
FINISHED |
| Object |
Likpe dialect
The Likpe dialect is a variety of the Siwu language spoken by the Likpe people in the Volta Region of Ghana.
|
E618736
|
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: Likpe dialect | Statement: [Siwu language, hasDialects, Likpe dialect]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Likpe dialect Context triple: [Siwu language, hasDialects, Likpe dialect]
-
A.
Sekopa dialect
The Sekopa dialect is a regional variety of the Northern Sotho language spoken by specific communities in South Africa, distinguished by its own phonological and lexical features.
-
B.
Tappalang dialect
The Tappalang dialect is a regional variety of the Mandar language spoken by Mandar communities in parts of West Sulawesi, Indonesia.
-
C.
Hunza dialect
The Hunza dialect is a regional variety of the Burushaski language spoken primarily in the Hunza Valley of northern Pakistan.
-
D.
Kewevkapaya dialect
The Kewevkapaya dialect is a regional variety of a Native American language closely related to and forming a continuum with the Wipukpa dialect.
-
E.
Balanipa dialect
The Balanipa dialect is a regional variety of the Mandar language spoken by communities in the Balanipa area of West Sulawesi, Indonesia.
- 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: Likpe dialect Triple: [Siwu language, hasDialects, Likpe dialect]
Generated description
The Likpe dialect is a variety of the Siwu language spoken by the Likpe people in the Volta Region of Ghana.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Likpe dialect Target entity description: The Likpe dialect is a variety of the Siwu language spoken by the Likpe people in the Volta Region of Ghana.
-
A.
Sekopa dialect
The Sekopa dialect is a regional variety of the Northern Sotho language spoken by specific communities in South Africa, distinguished by its own phonological and lexical features.
-
B.
Tappalang dialect
The Tappalang dialect is a regional variety of the Mandar language spoken by Mandar communities in parts of West Sulawesi, Indonesia.
-
C.
Hunza dialect
The Hunza dialect is a regional variety of the Burushaski language spoken primarily in the Hunza Valley of northern Pakistan.
-
D.
Kewevkapaya dialect
The Kewevkapaya dialect is a regional variety of a Native American language closely related to and forming a continuum with the Wipukpa dialect.
-
E.
Balanipa dialect
The Balanipa dialect is a regional variety of the Mandar language spoken by communities in the Balanipa area of West Sulawesi, Indonesia.
- 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_69c68812ef7c819099369f51febb725c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2496fa08190895d8b625fb0d699 |
completed | March 27, 2026, 6:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c712c75b9c819099b0be616925a0b9 |
completed | March 27, 2026, 11:29 p.m. |
| NEDg | Description generation | batch_69c7135106288190b5b20523c3efa229 |
completed | March 27, 2026, 11:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7141cd52c8190a783590ad1067840 |
completed | March 27, 2026, 11:34 p.m. |
Created at: March 27, 2026, 2:13 p.m.