Triple

T17670621
Position Surface form Disambiguated ID Type / Status
Subject Lematang people E440509 entity
Predicate administrativeRegion P285 FINISHED
Object Lahat Regency 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: Lahat Regency | Statement: [Lematang people, administrativeRegion, Lahat Regency]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lahat Regency
Context triple: [Lematang people, administrativeRegion, Lahat Regency]
  • A. Pelalawan Regency
    Pelalawan Regency is an administrative region in Riau Province on the island of Sumatra, Indonesia, known for its peatland forests, palm oil plantations, and riverine landscapes.
  • B. Kampar Regency
    Kampar Regency is an administrative region in Riau Province, Indonesia, known for its riverside landscapes, agricultural activities, and proximity to the Kampar River.
  • C. Dharmasraya Regency
    Dharmasraya Regency is an administrative regency in the southeastern part of West Sumatra, Indonesia, known for its historical links to the ancient Dharmasraya kingdom and its predominantly rural, agrarian communities.
  • D. Bulungan Regency
    Bulungan Regency is an administrative region in northern Borneo that serves as one of the key regencies of Indonesia’s North Kalimantan province.
  • E. Bengkalis Regency
    Bengkalis Regency is an administrative region in Riau Province, Indonesia, encompassing parts of the eastern Sumatran mainland and nearby islands including Rupat Island.
  • 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: Lahat Regency
Target entity description: Lahat Regency is an administrative region in South Sumatra, Indonesia, known for its diverse ethnic communities, including the indigenous Lematang people.
  • A. Pelalawan Regency
    Pelalawan Regency is an administrative region in Riau Province on the island of Sumatra, Indonesia, known for its peatland forests, palm oil plantations, and riverine landscapes.
  • B. Kampar Regency
    Kampar Regency is an administrative region in Riau Province, Indonesia, known for its riverside landscapes, agricultural activities, and proximity to the Kampar River.
  • C. Dharmasraya Regency
    Dharmasraya Regency is an administrative regency in the southeastern part of West Sumatra, Indonesia, known for its historical links to the ancient Dharmasraya kingdom and its predominantly rural, agrarian communities.
  • D. Bulungan Regency
    Bulungan Regency is an administrative region in northern Borneo that serves as one of the key regencies of Indonesia’s North Kalimantan province.
  • E. Bengkalis Regency
    Bengkalis Regency is an administrative region in Riau Province, Indonesia, encompassing parts of the eastern Sumatran mainland and nearby islands including Rupat Island.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46f68a038819084828ff73bcf1fcc completed April 19, 2026, 6 a.m.
Created at: April 10, 2026, 9:59 a.m.