Triple

T2193004
Position Surface form Disambiguated ID Type / Status
Subject Betsy Ross E49905 entity
Predicate alsoKnownAs P39 FINISHED
Object Betsy Ross E49905 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: Betsy Ross | Statement: [Betsy Ross, alsoKnownAs, Betsy Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betsy Ross
Context triple: [Betsy Ross, alsoKnownAs, Betsy Ross]
  • A. Betsy Ross chosen
    Betsy Ross was an American upholsterer and seamstress popularly credited with sewing the first American flag during the Revolutionary War.
  • B. Elizabeth Howe
    Elizabeth Howe was a Massachusetts woman executed for alleged witchcraft during the 1692 Salem witch trials, later recognized as one of its wrongfully accused victims.
  • C. Mary Pickersgill
    Mary Pickersgill was an American flag maker best known for creating the enormous Star-Spangled Banner flag that inspired the United States national anthem during the War of 1812.
  • D. Fanny Bowditch Dixwell
    Fanny Bowditch Dixwell was the wife of U.S. Supreme Court Justice Oliver Wendell Holmes Jr., known for her supportive role in his personal and professional life.
  • E. Lydia Reed
    Lydia Reed is an American former child actress best known for her film and television roles in the 1950s.
  • 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_69a88aaba3c48190b351cab9b26989ff completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbf4a542881908aaaf4f0f85bc32c completed March 7, 2026, 6:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5db283cc8190b75870cb2aabc5af completed March 9, 2026, 5:42 a.m.
Created at: March 4, 2026, 7:46 p.m.