Triple
T21053686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngulu language |
E518652
|
entity |
| Predicate | hasGlottologName |
P6521
|
FINISHED |
| Object | Ngulu |
—
|
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: Ngulu | Statement: [Ngulu language, hasGlottologName, Ngulu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngulu Context triple: [Ngulu language, hasGlottologName, Ngulu]
-
A.
Ngulu
chosen
Ngulu is a small inhabited island in the Ngulu Atoll of the Federated States of Micronesia, serving as the main settlement and administrative center of the atoll.
-
B.
Agulu
Agulu is a town in southeastern Nigeria known for its large natural lake and location within Anambra State.
-
C.
Ngala
Ngala is a Bantu ethnic group and language community primarily found in the Democratic Republic of the Congo.
-
D.
Ngala
Ngala is a local government area in Borno State, northeastern Nigeria, located near the border with Cameroon and affected by regional security challenges.
-
E.
Nguiu
Nguiu is the former name of Wurrumiyanga, a community on Bathurst Island in Australia's Northern Territory that is home to Tiwi people.
- 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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd7e087c81908712ddc63e8b1e6c |
completed | April 21, 2026, 4:30 a.m. |
Created at: April 16, 2026, 2:36 p.m.