Triple
T12929158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kikuyu people |
E309326
|
entity |
| Predicate | traditionalDeity |
P5606
|
FINISHED |
| Object | Ngai |
E919602
|
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: Ngai | Statement: [Kikuyu people, traditionalDeity, Ngai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngai Context triple: [Kikuyu people, traditionalDeity, Ngai]
-
A.
Ngai
chosen
Ngai is the supreme creator god in Kikuyu and several other East African traditional belief systems, associated with the sky, rain, and Mount Kenya.
-
B.
Runga
Runga are an ethnic group primarily found in the Central African Republic, Chad, and Sudan, known for their distinct language and cultural traditions.
-
C.
Te Kā
Te Kā is the fiery lava demon and corrupted form of the goddess Te Fiti who serves as the main antagonist in Disney's animated film "Moana."
-
D.
Ōhinehou
Ōhinehou is the traditional Māori name for the port town of Lyttelton in Canterbury, New Zealand.
-
E.
Onerahi
Onerahi is a coastal suburb of Whangārei in Northland, New Zealand, known for its harbour views and proximity to Whangārei Airport.
- 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_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971ec72a48190aceef10630603d2c |
completed | April 10, 2026, 9:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6af687f548190b70ac8fa9bbbd414 |
completed | May 3, 2026, 2:14 a.m. |
Created at: April 9, 2026, 5:42 p.m.