Triple

T8632030
Position Surface form Disambiguated ID Type / Status
Subject Sciurini E204424 entity
Predicate includesTaxon P1393 FINISHED
Object Myosciurus E737826 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: Myosciurus | Statement: [Sciurini, includesTaxon, Myosciurus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Myosciurus
Context triple: [Sciurini, includesTaxon, Myosciurus]
  • A. Myosciurus chosen
    Myosciurus is a genus of small African squirrels in the family Sciuridae, best known for the African pygmy squirrel, one of the world’s smallest squirrel species.
  • B. Nannosciurus
    Nannosciurus is a genus of small Neotropical squirrels in the tribe Sciurini, found primarily in Central and South American forests.
  • C. Urosciurus
    Urosciurus is a genus of Neotropical tree squirrels in the family Sciuridae, found primarily in the forests of Central and South America.
  • D. Syntheosciurus
    Syntheosciurus is a small genus of tree squirrels in the tribe Sciurini, known from Central American montane forests.
  • E. Sundasciurus
    Sundasciurus is a genus of Southeast Asian tree squirrels known for their arboreal habits and diversity across forested habitats in the Sunda region.
  • 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_69ca834b903c8190add96cc651e1a477 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc4742a89081909f9f7b3621e50b40 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cfd069faa481908db58399fe8f72f1 completed April 3, 2026, 2:36 p.m.
Created at: March 30, 2026, 6:27 p.m.