Triple

T21780923
Position Surface form Disambiguated ID Type / Status
Subject Prabu Padjadjaran E537708 entity
Predicate region P40 FINISHED
Object Tatar Sunda 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: Tatar Sunda | Statement: [Prabu Padjadjaran, region, Tatar Sunda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tatar Sunda
Context triple: [Prabu Padjadjaran, region, Tatar Sunda]
  • A. Sundanese chosen
    The Sundanese are an indigenous ethnic group of western Java in Indonesia, known for their distinct language, rich musical and dance traditions, and agrarian culture.
  • B. Tenggerese
    The Tenggerese are an indigenous Javanese ethnic group living around Mount Bromo in East Java, Indonesia, known for preserving Hindu traditions and distinctive highland farming culture.
  • C. Kedangese
    Kedangese is an Austronesian language spoken by the Kedang people on Lembata Island in eastern Indonesia.
  • D. Banjarese
    Banjarese is an Austronesian language spoken primarily by the Banjar people of South Kalimantan in Indonesia.
  • E. Asinan Betawi
    Asinan Betawi is a traditional Betawi pickled vegetable and fruit salad dish from Jakarta, typically served in a tangy, spicy vinegar-based brine.
  • 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_69e0c470759c819094a215757113562b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0462cae6481908d3e7f71683d8921 completed April 28, 2026, 5:31 a.m.
Created at: April 16, 2026, 6:52 p.m.