Triple

T883131
Position Surface form Disambiguated ID Type / Status
Subject Robert Brown E19070 entity
Predicate employer P7 FINISHED
Object British Museum E11098 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: British Museum | Statement: [Robert Brown, employer, British Museum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: British Museum
Context triple: [Robert Brown, employer, British Museum]
  • A. British Museum chosen
    The British Museum is one of the world’s largest and most comprehensive museums, renowned for its vast collection of art and antiquities spanning human history and cultures.
  • B. Victoria and Albert Museum
    The Victoria and Albert Museum is a major London museum renowned for its vast collections of decorative arts and design spanning centuries and cultures.
  • C. Natural History Museum, London
    The Natural History Museum in London is a major British institution renowned for its vast collections of specimens from natural history, iconic dinosaur displays, and grand Romanesque architecture in South Kensington.
  • D. Science Museum, London
    The Science Museum, London is a major museum in South Kensington renowned for its extensive collections and interactive exhibits on science, technology, engineering, and medicine.
  • E. British Library
    The British Library is the United Kingdom’s national library and one of the world’s largest research libraries, renowned for its vast collections of books, manuscripts, and historical documents.
  • 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_69a4939c32488190a7ccd41cf0abb22b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4accda4148190aa628dab14d7f5de completed March 1, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf55fec481908460522373cc48ba completed March 4, 2026, 6:21 a.m.
Created at: March 1, 2026, 7:39 p.m.