Triple
T4232651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aepycerotinae |
E94615
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Aepyceros |
E421780
|
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: Aepyceros | Statement: [Aepycerotinae, namedAfter, Aepyceros]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aepyceros Context triple: [Aepycerotinae, namedAfter, Aepyceros]
-
A.
Aepyceros
chosen
Aepyceros is a genus of African antelopes best known for including the impala, a medium-sized, agile species common in savanna and woodland habitats.
-
B.
Aepyceros melampus
Aepyceros melampus, commonly known as the impala, is a medium-sized African antelope renowned for its agility, leaping ability, and prominence in savanna ecosystems.
-
C.
Alcelaphus
Alcelaphus is a genus of African antelopes best known for including the hartebeest, a large, long-faced grazer of open savannas and grasslands.
-
D.
Damaliscus
Damaliscus is a genus of African antelopes in the subfamily Alcelaphinae, which includes species such as topi and tsessebe known for their speed and open-grassland habitats.
-
E.
Tragelaphus
Tragelaphus is a genus of spiral-horned African antelopes that includes species such as kudus, bushbucks, and nyalas.
- 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_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e65720c819087c4022c774ff7c3 |
completed | March 12, 2026, 11:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b77632d08190ab7c12986e2cee61 |
completed | March 14, 2026, 7:31 p.m. |
Created at: March 12, 2026, 11:05 p.m.