Triple
T16586817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kobus megaceros |
E402980
|
entity |
| Predicate | parentTaxon |
P2891
|
FINISHED |
| Object | Kobus |
E400415
|
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: Kobus | Statement: [Kobus megaceros, parentTaxon, Kobus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kobus Context triple: [Kobus megaceros, parentTaxon, Kobus]
-
A.
Kobus
chosen
Kobus is a genus of medium-sized African antelopes that includes species such as waterbucks and lechwes, typically associated with wetland and riverside habitats.
-
B.
Dawakin Kudu
Dawakin Kudu is a prominent town and local government area in northern Nigeria known for its role in agriculture and education within Kano State.
-
C.
Kenzi
Kenzi is a Nubian language spoken in southern Egypt, closely related to Nobiin and part of the broader Nubian language family along the Nile.
-
D.
Komo
Komo is a town located in Hela Province in the Highlands region of Papua New Guinea.
-
E.
Komo
The Komo are an ethnic group indigenous to western Ethiopia, particularly associated with the Gambela Region, with their own distinct language and cultural traditions.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3599daa508190a9ed6f64138c0e53 |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007da6d6f08190a8524b1c955b7c2e |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:16 a.m.