Triple
T2812002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akan |
E54191
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Akan Kasa |
E54191
|
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: Akan Kasa | Statement: [Akan, hasAlternativeName, Akan Kasa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akan Kasa Context triple: [Akan, hasAlternativeName, Akan Kasa]
-
A.
Akan
chosen
Akan is a major Central Tano language spoken primarily in Ghana and parts of Côte d’Ivoire, serving as a key lingua franca and cultural language for the Akan people.
-
B.
Aku Aku
Aku Aku is a sentient wooden mask who guides and protects Crash Bandicoot throughout the Crash Bandicoot video game series.
-
C.
Gambiri Kati
Gambiri Kati is an alternative name for the Tregami language, an Indo-Iranian language spoken in parts of eastern Afghanistan.
-
D.
Nyanjoga
Nyanjoga is a Kenyan surname associated with individuals such as Habiba Akumu Nyanjoga.
-
E.
Rakai Pikatan
Rakai Pikatan was a 9th-century Javanese king of the Medang (Mataram) Kingdom, known for consolidating royal power in Central Java and patronizing major Hindu temple construction.
- 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_69ab49de0af08190b3da69683be1e728 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde354a5881908cd3d545f7dda81c |
completed | March 7, 2026, 8:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afce9a76388190a5dce756de2eb59f |
completed | March 10, 2026, 7:56 a.m. |
Created at: March 6, 2026, 9:59 p.m.