Triple

T9977977
Position Surface form Disambiguated ID Type / Status
Subject Arverni E196379 entity
Predicate capital P234 FINISHED
Object Gergovia E560561 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: Gergovia | Statement: [Arverni, capital, Gergovia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gergovia
Context triple: [Arverni, capital, Gergovia]
  • A. Gergovia chosen
    Gergovia was an ancient Arvernian hilltop settlement in Gaul, best known as the site where Vercingetorix won a major victory over Julius Caesar during the Gallic Wars.
  • B. Belonia
    Belonia is a small town in the South Tripura district of the Indian state of Tripura, near the India–Bangladesh border.
  • C. Jamuria
    Jamuria is a coal-mining town in West Bengal, India, situated within the Raniganj coalfield region.
  • D. Phigalia
    Phigalia is an ancient town in Arcadia, Greece, known for its historical significance and nearby Temple of Apollo Epicurius at Bassae.
  • E. Genovia
    Genovia is a fictional European principality best known as the royal setting of Meg Cabot’s "The Princess Diaries" series and its film adaptations.
  • 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_69ca82efbce081908179b4b9c65096eb completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb84ef8ac8190abbe78b7611c5309 completed April 2, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69d257d3fc308190b82b3731139d15cb completed April 5, 2026, 12:38 p.m.
Created at: March 30, 2026, 8:48 p.m.