Triple

T20599451
Position Surface form Disambiguated ID Type / Status
Subject Pagaruyung E506134 entity
Predicate partOf P40 FINISHED
Object Minangkabau cultural landscape NE NERFINISHED

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: Minangkabau cultural landscape | Statement: [Pagaruyung, partOf, Minangkabau cultural landscape]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Minangkabau cultural landscape
Context triple: [Pagaruyung, partOf, Minangkabau cultural landscape]
  • A. Sasak cultural landscape
    The Sasak cultural landscape is a traditional cultural region on the island of Lombok in Indonesia, characterized by indigenous Sasak villages, vernacular architecture, and enduring agrarian and weaving practices.
  • B. Sukur Cultural Landscape
    Sukur Cultural Landscape is a historic terraced settlement in northeastern Nigeria renowned for its traditional stone architecture, sacred Hidi palace complex, and long-standing cultural and spiritual significance to the Sukur people.
  • C. Bokoharjo cultural landscape
    Bokoharjo cultural landscape is a traditional Javanese rural area in Klaten Regency known for its agricultural heritage, cultural practices, and historical sites.
  • D. Tegallalang rice terraces
    Tegallalang rice terraces are a famous, photogenic series of stepped rice paddies in Bali known for their lush landscapes and traditional subak irrigation system.
  • E. Dragon’s Backbone Rice Terraces
    Dragon’s Backbone Rice Terraces is a famous, centuries-old system of spectacularly layered rice paddies carved into the mountains of Longsheng County in Guangxi, China.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Minangkabau cultural landscape
Target entity description: The Minangkabau cultural landscape is a highland region of West Sumatra characterized by matrilineal Minangkabau society, distinctive horn-shaped roof architecture, rice terraces, and a long-standing integration of customary law with Islam.
  • A. Sasak cultural landscape
    The Sasak cultural landscape is a traditional cultural region on the island of Lombok in Indonesia, characterized by indigenous Sasak villages, vernacular architecture, and enduring agrarian and weaving practices.
  • B. Sukur Cultural Landscape
    Sukur Cultural Landscape is a historic terraced settlement in northeastern Nigeria renowned for its traditional stone architecture, sacred Hidi palace complex, and long-standing cultural and spiritual significance to the Sukur people.
  • C. Bokoharjo cultural landscape
    Bokoharjo cultural landscape is a traditional Javanese rural area in Klaten Regency known for its agricultural heritage, cultural practices, and historical sites.
  • D. Tegallalang rice terraces
    Tegallalang rice terraces are a famous, photogenic series of stepped rice paddies in Bali known for their lush landscapes and traditional subak irrigation system.
  • E. Dragon’s Backbone Rice Terraces
    Dragon’s Backbone Rice Terraces is a famous, centuries-old system of spectacularly layered rice paddies carved into the mountains of Longsheng County in Guangxi, China.
  • F. None of above. chosen

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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa1ef9ac8190b05e23c149529cb9 completed April 20, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:40 a.m.