Triple

T27233885
Position Surface form Disambiguated ID Type / Status
Subject Captain Haddock E682224 entity
Predicate usesExpression P162524 FINISHED
Object Thundering typhoons LITERAL 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: Thundering typhoons | Statement: [Captain Haddock, usesExpression, Thundering typhoons]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usesExpression
Context triple: [Captain Haddock, usesExpression, Thundering typhoons]
  • A. usedInExpression
    Indicates that one entity (typically a term, symbol, or construct) is employed as a component within another entity that represents an expression.
  • B. usesExpressionSystem
    Indicates that one entity employs or relies on a particular expression system (e.g., a biological, genetic, or computational framework) to produce, express, or manipulate another entity.
  • C. usesTextExpression
    Indicates that one entity employs or represents another entity through a textual expression or string-based form.
  • D. hasExpression
    Indicates that an entity displays or possesses a particular facial or emotional expression.
  • E. isPartOfExpression
    Indicates that something functions as a component or constituent element within a larger expression.
  • F. None of above. chosen

Provenance (4 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_69eefacdad7881908b7bca61c90a1a1e completed April 27, 2026, 5:57 a.m.
NER Named-entity recognition batch_69f62b9e5ba88190a3c0d46edec7afe7 completed May 2, 2026, 4:51 p.m.
PD Predicate disambiguation batch_69f623a91b9c8190b2e2fdbc55cb89b6 completed May 2, 2026, 4:17 p.m.
PDg Predicate description generation batch_69f625402d808190be8279d895d2b27f completed May 2, 2026, 4:24 p.m.
Created at: April 27, 2026, 9:47 a.m.