Triple

T12853310
Position Surface form Disambiguated ID Type / Status
Subject Benjamin Franklin E307379 entity
Predicate paternalGrandfather P979 FINISHED
Object Thomas Franklin E307379 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: Thomas Franklin | Statement: [Benjamin Franklin, paternalGrandfather, Thomas Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Franklin
Context triple: [Benjamin Franklin, paternalGrandfather, Thomas Franklin]
  • A. Thomas Franklin chosen
    Thomas Franklin was the paternal grandfather of Benjamin Franklin and an English blacksmith from Northamptonshire.
  • B. John Maxwell Adams
    John Maxwell Adams was the father of Joan Mondale, who was the wife of former U.S. Vice President Walter Mondale.
  • C. William Cleveland
    William Cleveland was the son of Richard Falley Cleveland and a member of the family of U.S. President Grover Cleveland.
  • D. Arthur Stanley Jefferson
    Arthur Stanley Jefferson, better known as Stan Laurel, was a British-born comic actor, writer, and director famed as one half of the legendary film comedy duo Laurel and Hardy.
  • E. John Coolidge Adams
    John Coolidge Adams is a prominent American composer known for his influential contributions to contemporary classical music and minimalism, including works like "Nixon in China" and "Short Ride in a Fast Machine."
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97021df7481909cd42a0f72040aa5 completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69ba79918819093e047ce22191923 completed May 3, 2026, 12:49 a.m.
Created at: April 9, 2026, 5:36 p.m.