Triple

T14477434
Position Surface form Disambiguated ID Type / Status
Subject Jane Griffin E359008 entity
Predicate title P38 FINISHED
Object Lady Franklin E1101794 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: Lady Franklin | Statement: [Jane Griffin, title, Lady Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lady Franklin
Context triple: [Jane Griffin, title, Lady Franklin]
  • A. Lady Franklin chosen
    Lady Franklin, born Jane Griffin, was a prominent 19th-century British explorer’s wife and patron best known for her tireless efforts to discover the fate of her husband, Arctic explorer Sir John Franklin.
  • B. Henrietta
    Henrietta is a feminine given name of English origin, historically popular in the 18th and 19th centuries and borne by several notable figures.
  • C. Henrietta
    Henrietta is a suburban community in western New York State, located near Rochester within the Rust Belt region along the Interstate 90 corridor.
  • D. Adria Fanny Heath
    Adria Fanny Heath was the mother of Lord Chelmsford, a British peer and colonial administrator.
  • E. Goodricke
    Goodricke is a surname of English origin, historically borne by several notable figures including astronomer John Goodricke.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9248edb48190a74eb032aeaac027 completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d8ccd608190afd23c903cd5686a completed May 8, 2026, 4:58 a.m.
Created at: April 10, 2026, 1:20 a.m.