Triple
T15500128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guahibo |
E378929
|
entity |
| Predicate | neighboringIndigenousPeoples |
P11274
|
FINISHED |
| Object | Sikuani |
E351317
|
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: Sikuani | Statement: [Guahibo, neighboringIndigenousPeoples, Sikuani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sikuani Context triple: [Guahibo, neighboringIndigenousPeoples, Sikuani]
-
A.
Sikuani
chosen
The Sikuani are an Indigenous people of the Colombian and Venezuelan Llanos, known for their semi-nomadic traditions, rich oral culture, and Guahiboan language.
-
B.
Kasangati
Kasangati is a town in central Uganda that serves as a growing commercial and residential hub within the Greater Kampala metropolitan area.
-
C.
Kinyara
Kinyara is a town in Uganda’s Masindi District, best known for its large sugar estate and associated agro-industrial activities.
-
D.
Manyoni
Manyoni is a town and district headquarters in central Tanzania known for its location along major road and rail routes in the Singida Region.
-
E.
Shiyali
Shiyali is the given name of S. R. Ranganathan, the influential Indian mathematician and librarian known as the father of library science in India.
- 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_69d85cd53a7c819080f5b9042c4c199e |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03fcb4e8c81908e4ab463e3ae252b |
completed | April 16, 2026, 1:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3667a53c81908be789f99e580265 |
completed | May 9, 2026, 1:28 p.m. |
Created at: April 10, 2026, 3:54 a.m.