Triple

T7992194
Position Surface form Disambiguated ID Type / Status
Subject Sumner Welles E186034 entity
Predicate spouse P13 FINISHED
Object Harriet Appleton Post E186034 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: Harriet Appleton Post | Statement: [Sumner Welles, spouse, Harriet Appleton Post]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harriet Appleton Post
Context triple: [Sumner Welles, spouse, Harriet Appleton Post]
  • A. Harriet Appleton Post chosen
    Harriet Appleton Post was an American socialite best known as the first wife of prominent U.S. diplomat Sumner Welles.
  • B. Mary Scott Harrison
    Mary Scott Harrison was the daughter of U.S. President Benjamin Harrison and First Lady Caroline Harrison, known as a member of the prominent Harrison political family.
  • C. Martha McMillan Roberts
    Martha McMillan Roberts was a Farm Security Administration photographer known for documenting American life during the Great Depression era.
  • D. Margaret Hayes
    Margaret Hayes was an American film and television actress active in the mid-20th century, known for her supporting roles in dramas and crime films.
  • E. Elizabeth F. Churchill
    Elizabeth F. Churchill is a prominent human-computer interaction researcher and design leader known for her influential contributions to user experience, social computing, and the HCI community.
  • 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_69ca829c6c308190ab05b43d234c52b2 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c712d0481908d163d2509d054fa completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe0fe312c81908c6874fa0aabe7d5 completed March 31, 2026, 2:58 p.m.
Created at: March 30, 2026, 5:16 p.m.