Triple

T8467308
Position Surface form Disambiguated ID Type / Status
Subject Xerus E200195 entity
Predicate hasSpecies P965 FINISHED
Object Xerus princeps E200195 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: Xerus princeps | Statement: [Xerus, hasSpecies, Xerus princeps]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xerus princeps
Context triple: [Xerus, hasSpecies, Xerus princeps]
  • A. Xerus chosen
    Xerus is a genus of African ground squirrels known for their diurnal, social behavior and adaptation to open, arid habitats.
  • B. Atlantoxerus
    Atlantoxerus is a genus of ground-dwelling squirrels native to North Africa, best known for the Barbary ground squirrel.
  • C. Mecistops
    Mecistops is a genus of slender-snouted African crocodiles known for their elongated, narrow snouts adapted for catching fish.
  • D. Melursus
    Melursus is a genus of bears best known for the sloth bear, a shaggy-coated, insect-eating bear native to the Indian subcontinent.
  • E. Maurus
    Maurus is a masculine given name of Latin origin, historically associated with early Christian saints and used as a variant of names like Maurice.
  • 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_69ca831a4f348190bfdd09250e86ae35 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4d2eb648190b606411eb6a8f7ea completed March 31, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf423bade4819094204d98303093c8 completed April 3, 2026, 4:29 a.m.
Created at: March 30, 2026, 6:11 p.m.