Triple

T6180952
Position Surface form Disambiguated ID Type / Status
Subject Pombal E137939 entity
Predicate partOfGeographicalRegion P64798 FINISHED
Object Sertão of Paraíba E559478 NE FINISHED

How this triple was built (3 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: Sertão of Paraíba | Statement: [Pombal, partOfGeographicalRegion, Sertão of Paraíba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sertão of Paraíba
Context triple: [Pombal, partOfGeographicalRegion, Sertão of Paraíba]
  • A. Sertão Sergipano
    Sertão Sergipano is the semi-arid hinterland region of the Brazilian state of Sergipe, characterized by dry climate, caatinga vegetation, and traditional rural communities.
  • B. sertão of Paraíba chosen
    The sertão of Paraíba is a semi-arid inland region of the Brazilian state of Paraíba, characterized by its dry climate, scrubby vegetation, and traditional cattle-raising and agricultural communities.
  • C. Agreste Sergipano
    Agreste Sergipano is a semi-arid transitional subregion of the Brazilian state of Sergipe, characterized by mixed agricultural activity and a landscape between the coastal zone and the sertão.
  • D. Brejo Paraibano
    Brejo Paraibano is a traditional microregion in the state of Paraíba, Brazil, known for its mild climate, green landscapes, and cultural and historical significance within the Agreste zone.
  • E. Zona da Mata Paraibana
    Zona da Mata Paraibana is a coastal forested region in the state of Paraíba, Brazil, known for its humid climate, Atlantic Forest remnants, and agricultural activities such as sugarcane cultivation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: partOfGeographicalRegion
Context triple: [Pombal, partOfGeographicalRegion, Sertão of Paraíba]
  • A. subregionOf
    Indicates that one region is geographically or administratively contained within, and is a part of, another larger region.
  • B. geographicalRegionType
    Indicates the specific kind or category of geographical region that an entity belongs to (e.g., continent, country, province, or city).
  • C. partOfTerritory
    Indicates that one geographic or administrative area is contained within, and forms a constituent portion of, another territory.
  • D. placeRegion chosen
    Indicates that a place is located within, or is part of, a larger geographic or administrative region.
  • E. region1
    Indicates that one entity is the first or primary region associated with, containing, or encompassing another entity.
  • F. None of above.

Provenance (4 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_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c060fdf7ac8190a0e887907ec9a922 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141c30d28819095d719adc421b02d completed March 23, 2026, 1:36 p.m.
PD Predicate disambiguation batch_69c055fa0a808190bda37832e3ac150c completed March 22, 2026, 8:50 p.m.
Created at: March 22, 2026, 4:18 p.m.