Triple

T5003834
Position Surface form Disambiguated ID Type / Status
Subject Théâtre antique de Vienne E112436 entity
Predicate hasView P854 FINISHED
Object city of Vienne E487013 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: city of Vienne | Statement: [Théâtre antique de Vienne, hasView, city of Vienne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Vienne
Context triple: [Théâtre antique de Vienne, hasView, city of Vienne]
  • A. City of Vienne chosen
    The City of Vienne is a historic commune in southeastern France, renowned for its rich Roman heritage and well-preserved ancient monuments.
  • B. town of Vienne
    The town of Vienne is a historic commune in southeastern France on the Rhône River, renowned for its well-preserved Roman and medieval heritage.
  • C. Vaison-la-Romaine
    Vaison-la-Romaine is a historic town in southeastern France renowned for its extensive Roman archaeological sites and medieval architecture.
  • D. Souillac
    Souillac is a picturesque town in southwestern France known for its historic architecture and scenic setting along the Dordogne River.
  • E. Ville de Valence
    Ville de Valence is the municipal government of the French city of Valence, responsible for local administration, public services, and cultural institutions.
  • 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_69bd4433d0b08190877e83959ef40d81 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72e49b048190bac55d9e7a6f7963 completed March 20, 2026, 4:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea470ca3c81909e24b18e1e609dbd completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:35 p.m.