Triple

T703702
Position Surface form Disambiguated ID Type / Status
Subject Harland and Wolff E14053 entity
Predicate historicalPeakEmployment P4936 FINISHED
Object tens of thousands of workers 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: tens of thousands of workers | Statement: [Harland and Wolff, historicalPeakEmployment, tens of thousands of workers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: historicalPeakEmployment
Context triple: [Harland and Wolff, historicalPeakEmployment, tens of thousands of workers]
  • A. unemploymentPeak
    Indicates that the level of unemployment has reached its highest point within a specified time period or context.
  • B. historicalPeak chosen
    Indicates that the related value or state represents the highest level ever reached by something within a historical or recorded time frame.
  • C. historicalPeakIndustrialPeriod
    Indicates the time period during which an entity reached its highest level of industrial activity or development.
  • D. populationAtPeak
    Indicates that an entity’s population size is measured at its highest recorded level during a specified time or condition.
  • E. historicalEconomicBase
    Indicates the primary type of economic activity or production that historically underpinned or sustained an entity’s economy.
  • F. None of above.

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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a58d4c3c8190ad4527d14bca5e6e completed March 1, 2026, 8:46 p.m.
PD Predicate disambiguation batch_69a4a4edc33881909a978268f6dd5d82 completed March 1, 2026, 8:43 p.m.
Created at: March 1, 2026, 7:36 p.m.