Triple

T19200397
Position Surface form Disambiguated ID Type / Status
Subject Randolph Peter Best E470090 entity
Predicate placeOfBirth P1 FINISHED
Object Madras 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: Madras | Statement: [Randolph Peter Best, placeOfBirth, Madras]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madras
Context triple: [Randolph Peter Best, placeOfBirth, Madras]
  • A. Madras
    Madras is a small city in central Oregon known as an agricultural hub and gateway to outdoor recreation in the surrounding high desert region.
  • B. Madras
    Madras is an unincorporated community located in Coweta County in the U.S. state of Georgia.
  • C. Vellore
    Vellore is a residential neighbourhood in the city of Vaughan, Ontario, known for its suburban housing, schools, and community amenities.
  • D. Vellore
    Vellore is a historic city in southern India known for its fort, educational and medical institutions, and location along the Palar River in the state of Tamil Nadu.
  • E. Madras, India chosen
    Madras, India—now known as Chennai—is a major coastal metropolis in South India and the capital of the state of Tamil Nadu.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f997879c8190ae7618d1ba0cede9 completed April 20, 2026, 10:01 a.m.
Created at: April 10, 2026, 12:07 p.m.