Triple

T5666697
Position Surface form Disambiguated ID Type / Status
Subject Vredefort E124873 entity
Predicate hasNearbyCity P350 FINISHED
Object Parys E127889 NE FINISHED

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: Parys | Statement: [Vredefort, hasNearbyCity, Parys]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parys
Context triple: [Vredefort, hasNearbyCity, Parys]
  • A. Parys chosen
    Parys is a small South African town in the Free State province, known for its scenic setting on the Vaal River and proximity to the Vredefort Dome, a UNESCO World Heritage-listed impact crater.
  • B. Koropi
    Koropi is a town in the Athens metropolitan area of Greece, known as the seat of the municipality of Kropia and a local hub in the Mesogeia plain.
  • C. Putna
    Putna is a village in Suceava County, Romania, best known as a major Romanian Orthodox pilgrimage site centered around the historic Putna Monastery.
  • D. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • E. Piershil
    Piershil is a small village in the Dutch province of South Holland, known for its rural character and location on the island of Hoeksche Waard.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c00828906881908966f270b8f130cf completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02345004081908858867be48d3885 completed March 22, 2026, 5:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04dad0af4819088280f2d97173e9e completed March 22, 2026, 8:14 p.m.
Created at: March 22, 2026, 3:43 p.m.