Triple

T3702719
Position Surface form Disambiguated ID Type / Status
Subject Roald Hoffmann E80816 entity
Predicate hasWork P6260 FINISHED
Object O, Bruto E196026 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: O, Bruto | Statement: [Roald Hoffmann, hasWork, O, Bruto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: O, Bruto
Context triple: [Roald Hoffmann, hasWork, O, Bruto]
  • A. Brutus
    Brutus was a Dutch warship that was captured by the British Royal Navy during the 1797 Battle of Camperdown in the French Revolutionary Wars.
  • B. Marcus Junius Brutus chosen
    Marcus Junius Brutus was a Roman senator best known as one of the leading conspirators in the assassination of Julius Caesar in 44 BC.
  • C. Cassius
    Cassius is the birth name of Muhammad Ali, the legendary American heavyweight boxing champion and civil rights figure.
  • D. Gaius Cassius Longinus
    Gaius Cassius Longinus was a Roman senator and leading instigator of the conspiracy that assassinated Julius Caesar in 44 BC.
  • E. Cinna
    Cinna is a key supporting character in "The Hunger Games" series, best known as Katniss Everdeen’s creative and compassionate stylist who subtly rebels against the Capitol through his designs.
  • 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_69ad8b1793888190a5f70e4b21dc05a1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc54925b48190b23d2a14ef825abc completed March 8, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cdf53190819098529d11a5a3c7a8 completed March 14, 2026, 2:54 a.m.
Created at: March 8, 2026, 3:33 p.m.