Triple

T21857951
Position Surface form Disambiguated ID Type / Status
Subject Pangandaran E539681 entity
Predicate capital P234 FINISHED
Object Parigi 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: Parigi | Statement: [Pangandaran, capital, Parigi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parigi
Context triple: [Pangandaran, capital, Parigi]
  • A. Parigi
    Parigi is a town located in the Vikarabad district of the Indian state of Telangana.
  • B. Parigi chosen
    Parigi is a coastal town that serves as the administrative center of Parigi Moutong Regency in Central Sulawesi, Indonesia.
  • C. Parisi
    Parisi is an Italian surname most notably associated with Giorgio Parisi, a Nobel Prize–winning theoretical physicist known for his work on complex systems and statistical mechanics.
  • D. Parisii
    The Parisii were a Celtic tribe of the Iron Age and Roman period who lived in the area of present-day Paris along the Seine River.
  • E. Paris
    Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
  • 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_69e0c47829648190bbe2d1d7033768ec completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0d638721c8190918fc6ad9c5d5bf6 completed April 28, 2026, 3:46 p.m.
Created at: April 16, 2026, 6:56 p.m.