Triple
T19954342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madoqua kirkii |
E479643
|
entity |
| Predicate | parentTaxon |
P2891
|
FINISHED |
| Object | Madoqua |
—
|
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: Madoqua | Statement: [Madoqua kirkii, parentTaxon, Madoqua]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madoqua Context triple: [Madoqua kirkii, parentTaxon, Madoqua]
-
A.
Madoqua
chosen
Madoqua is a genus of small African antelopes commonly known as dik-diks, characterized by their diminutive size, elongated snouts, and monogamous pair bonds.
-
B.
Bamiléké
The Bamiléké are a major Central African ethnic group of Cameroon known for their rich cultural traditions, entrepreneurial spirit, and densely populated chiefdoms in the country’s western highlands.
-
C.
Ngola
Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
-
D.
Ngola
Ngola was the royal title used by the rulers of the historical Kingdom of Ndongo in what is now Angola.
-
E.
Sena of Tete
Sena of Tete is a regional variety of the Sena Bantu language spoken primarily in and around the Tete province of Mozambique.
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65aef16588190b3a40a3d49ef5080 |
completed | April 20, 2026, 4:57 p.m. |
Created at: April 10, 2026, 1:54 p.m.