Triple

T19780922
Position Surface form Disambiguated ID Type / Status
Subject Southern Land E475128 entity
Predicate label P38 FINISHED
Object Southern Land NE NERFINISHED

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: Southern Land | Statement: [Southern Land, label, Southern Land]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Southern Land
Context triple: [Southern Land, label, Southern Land]
  • A. Southern Land chosen
    Southern Land is the literal English meaning of the Latin term "Terra Australis," historically used to refer to a hypothetical great southern continent.
  • B. Terra da Garoa
    Terra da Garoa is a popular nickname for the Brazilian metropolis of São Paulo, alluding to its characteristic light, misty rain.
  • C. Terra do Sal
    Terra do Sal is a nickname for Mossoró, a city in Brazil’s Rio Grande do Norte state known for its significant salt production.
  • D. Skyland
    Skyland is a mountain resort area in Shenandoah National Park, Virginia, known for its scenic vistas along Skyline Drive.
  • E. The Continent
    The Continent is the main fictional landmass in The Witcher universe, a war-torn, magic-infused world inhabited by humans, monsters, sorcerers, and non-human races.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653846a248190adc4afe0dc29a402 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.