Triple
T8851306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ga-Adangbe |
E210643
|
entity |
| Predicate | ethnolinguisticGroup |
P3349
|
FINISHED |
| Object | Ga-Dangme |
E182937
|
NE FINISHED |
How this triple was built (2 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: Ga-Dangme | Statement: [Ga-Adangbe, ethnolinguisticGroup, Ga-Dangme]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ga-Dangme Context triple: [Ga-Adangbe, ethnolinguisticGroup, Ga-Dangme]
-
A.
Ga-Dangme
chosen
Ga-Dangme are an ethnic group of southeastern Ghana, historically known as coastal traders and fishermen with a rich cultural heritage and distinct Ga and Dangme language varieties.
-
B.
Ga-Dangme people
The Ga-Dangme people are an ethnic group of southeastern Ghana, centered around the Greater Accra Region, known for their coastal trading history, distinctive festivals, and Ga and Dangme languages.
-
C.
Dangmechhu
Dangmechhu is a river flowing through Bhutan’s Royal Manas National Park, contributing to the park’s rich freshwater and wildlife habitats.
-
D.
Kpelle
Kpelle is a major Mande language spoken primarily in Liberia and Guinea by the Kpelle people.
-
E.
Dholuo
Dholuo is a Nilotic language spoken primarily by the Luo people of western Kenya and parts of Tanzania.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca838a424c8190b1ecac115c2927e7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60c2300c819097b1ca6ebe2f749a |
completed | April 1, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa08315fc8190b901adfc76348e18 |
completed | April 3, 2026, 11:12 a.m. |
Created at: March 30, 2026, 6:49 p.m.