Triple

T12620582
Position Surface form Disambiguated ID Type / Status
Subject Frank E301367 entity
Predicate shortFormOf P43 FINISHED
Object Franklin unclear NED1 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: Franklin | Statement: [Frank, shortFormOf, Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franklin
Context triple: [Frank, shortFormOf, Franklin]
  • A. Franklin
    Franklin McCain was an American civil rights activist best known as one of the Greensboro Four who led the 1960 Woolworth’s lunch counter sit-in in North Carolina.
  • B. Franklin
    Franklin is a town in Norfolk County, Massachusetts, serving as a terminus for the MBTA Commuter Rail system.
  • C. Franklin
    Franklin is a wealthy, hospitable landowner and one of the storytellers in Geoffrey Chaucer’s The Canterbury Tales, known for his focus on gentility and marital harmony.
  • D. Franklin
    Franklin is an independent city in southeastern Virginia known for its small-town character and historical ties to the regional lumber and paper industries.
  • E. Franklin
    Franklin is the middle name of William Franklin Graham Jr., better known as the American evangelist Billy Graham.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d960c75c9c819092265ebc2b39f21d completed April 10, 2026, 8:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65ed6f79881908872c644a9789f04 completed May 2, 2026, 8:30 p.m.
Created at: April 9, 2026, 5:13 p.m.