Triple

T4011827
Position Surface form Disambiguated ID Type / Status
Subject African Veldt E90661 entity
Predicate recreatesHabitat P30763 FINISHED
Object African savanna LITERAL 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: African savanna | Statement: [African Veldt, recreatesHabitat, African savanna]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: recreatesHabitat
Context triple: [African Veldt, recreatesHabitat, African savanna]
  • A. simulatesHabitatOf chosen
    Indicates that one entity artificially recreates or models the living conditions or environment characteristic of another entity’s natural habitat.
  • B. recreated
    Indicates that an entity has been created again or restored, typically after being removed, destroyed, or significantly altered.
  • C. formerHabitat
    Indicates that a location once served as a habitat for an entity but no longer does.
  • D. featuresHabitat
    Indicates that something includes or provides a particular habitat as part of its characteristics or environment.
  • E. domesticationCenter
    Indicates the place or region where a species was first brought under human control and selectively bred, marking the origin of its domestication.
  • F. None of above.

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_69aed95e44088190aff7d90a151b1b20 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefaec08dc8190a341809059554f84 completed March 9, 2026, 4:53 p.m.
PD Predicate disambiguation batch_69aef8fa6fec81909b1190ecbba61410 completed March 9, 2026, 4:44 p.m.
Created at: March 9, 2026, 3:34 p.m.