Triple
T19483772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Deep |
E487456
|
entity |
| Predicate | protagonist |
P268
|
FINISHED |
| Object | Yetu |
—
|
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: Yetu | Statement: [The Deep, protagonist, Yetu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yetu Context triple: [The Deep, protagonist, Yetu]
-
A.
Yetu
chosen
Yetu is the protagonist of Nnedi Okorafor’s novella "The Deep," a memory-bearing historian of an underwater people descended from enslaved Africans thrown overboard.
-
B.
Thotiana
"Thotiana" is a breakout 2018 hip-hop single by rapper Blueface that gained widespread popularity for its offbeat flow, viral dance, and numerous high-profile remixes.
-
C.
Shetebo
Shetebo are an indigenous people of the Peruvian Amazon closely related culturally and linguistically to the Shipibo-Conibo.
-
D.
Ntumu
Ntumu is a dialect of the Fang language spoken by Fang communities in parts of Central Africa, particularly in Equatorial Guinea, Gabon, and Cameroon.
-
E.
Byamee
Byamee is an alternate name for Baiame, the creator and sky father figure in several Aboriginal Australian mythologies.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6343c23308190a35f462f95338651 |
completed | April 20, 2026, 2:12 p.m. |
Created at: April 10, 2026, 1:39 p.m.