Triple

T12613357
Position Surface form Disambiguated ID Type / Status
Subject Red-Headed Woman E301183 entity
Predicate starring P1507 FINISHED
Object Henry Stephenson E69546 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 Stephenson | Statement: [Red-Headed Woman, starring, Henry Stephenson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Henry Stephenson
Context triple: [Red-Headed Woman, starring, Henry Stephenson]
  • A. Henry Stephenson chosen
    Henry Stephenson was a British character actor known for his dignified, often aristocratic roles in Hollywood films of the 1930s and 1940s.
  • B. Thomas Fairbairn
    Thomas Fairbairn was a prominent 19th-century British industrialist and art patron known for his leading role in organizing major art exhibitions in Manchester.
  • C. William Jaggard
    William Jaggard was a London printer and publisher best known for producing the 1623 First Folio of Shakespeare’s plays.
  • D. Henry Bell
    Henry Bell was a Scottish engineer and pioneer of steamship navigation, best known for operating one of Europe's first successful passenger steamboats in the early 19th century.
  • E. Henry Bell
    Henry Bell was a 17th-century English architect and mayor of King's Lynn, noted for designing prominent Baroque-style civic and commercial buildings.
  • 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_69d7bdeaf49c8190b13800111fa77ea3 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d960c2e5b88190a7cc16002b218d8a completed April 10, 2026, 8:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ed1044c8190bbe881d32a4bf29e completed May 2, 2026, 8:30 p.m.
Created at: April 9, 2026, 5:12 p.m.