Triple

T15031888
Position Surface form Disambiguated ID Type / Status
Subject Catherine Livingston E378372 entity
Predicate spouse P13 FINISHED
Object Henry Wheaton E78025 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: Henry Wheaton | Statement: [Catherine Livingston, spouse, Henry Wheaton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry Wheaton
Context triple: [Catherine Livingston, spouse, Henry Wheaton]
  • A. Henry Wheaton chosen
    Henry Wheaton was a 19th-century American jurist, diplomat, and pioneering scholar of international law whose writings significantly shaped the field.
  • B. William LeBaron
    William LeBaron was an American film producer and studio executive active during the early 20th century, known for overseeing numerous Hollywood productions in the 1920s and 1930s.
  • C. Henry Bayfield
    Henry Bayfield was a British naval officer and hydrographer known for his extensive 19th-century surveys and mapping of the Great Lakes region of North America.
  • D. Hamilton Wilkes
    Hamilton Wilkes was a 19th-century American yachtsman best known for helping establish the prestigious New York Yacht Club.
  • E. Williams Lea
    Williams Lea is a global business process outsourcing and professional services company specializing in document, information, and customer communication management for corporate clients.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e2416081908dfba48d7f7b4a84 completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69feae0be8bc81909e1f9ed31bfd76fb completed May 9, 2026, 3:46 a.m.
Created at: April 10, 2026, 2:59 a.m.