Triple

T1183579
Position Surface form Disambiguated ID Type / Status
Subject Roman Forum E25194 entity
Predicate contains P35 FINISHED
Object Regia E42850 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: Regia | Statement: [Roman Forum, contains, Regia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regia
Context triple: [Roman Forum, contains, Regia]
  • A. Regia chosen
    Regia was an important ancient building in the Roman Forum that served as the traditional residence and administrative center of Rome’s early kings and later the pontifex maximus.
  • B. Brida
    Brida is a novel by Brazilian author Paulo Coelho that follows a young Irish woman’s spiritual journey as she explores witchcraft, love, and self-discovery.
  • C. Mr. Director
    Mr. Director is the formal style of address used for the Cabinet-level head of the United States Office of Management and Budget.
  • D. Kingdom
    Kingdom is a British television drama series set in a small Norfolk town, following the life and legal practice of a local solicitor and his eccentric family and clients.
  • E. Corte
    Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
  • 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd37b4a88190bb71a2d272c5fd1a completed March 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f21547c81909cf23c454436e839 completed March 7, 2026, 6:32 p.m.
Created at: March 1, 2026, 7:45 p.m.