Triple
T21309420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pokomo people |
E525288
|
entity |
| Predicate | subgroup |
P10
|
FINISHED |
| Object | Upper Pokomo |
—
|
NE NERFINISHED |
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: Upper Pokomo | Statement: [Pokomo people, subgroup, Upper Pokomo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upper Pokomo Context triple: [Pokomo people, subgroup, Upper Pokomo]
-
A.
Upper Pokomo
chosen
Upper Pokomo is a dialect spoken by the Pokomo people of Kenya along the Tana River, forming one of the main varieties of the Pokomo language.
-
B.
Lower Pokomo
Lower Pokomo is a dialect of the Pokomo language spoken by communities living along the lower reaches of the Tana River in Kenya.
-
C.
Cuemba River
The Cuemba River is a watercourse in Angola that flows through Malanje Province, contributing to the region’s local hydrology and ecosystems.
-
D.
Komo River
The Komo River is a significant waterway in western Gabon that flows into the Atlantic Ocean near the capital city, Libreville.
-
E.
Kagini River
Kagini River is a tributary watercourse in India that feeds into the larger Bhima River system.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b518b8948190ad69cf9a8784d397 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e75aa916548190a11f8bb4255e3fed |
completed | April 21, 2026, 11:08 a.m. |
Created at: April 16, 2026, 4:06 p.m.