Triple

T12773624
Position Surface form Disambiguated ID Type / Status
Subject Nancy Lammeter E305311 entity
Predicate loveInterestOf P7325 FINISHED
Object Godfrey Cass E305310 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: Godfrey Cass | Statement: [Nancy Lammeter, loveInterestOf, Godfrey Cass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Godfrey Cass
Context triple: [Nancy Lammeter, loveInterestOf, Godfrey Cass]
  • A. Godfrey Cass chosen
    Godfrey Cass is a central character in George Eliot’s novel "Silas Marner," known as a morally conflicted landowner whose secret past and weak resolve shape much of the story’s drama.
  • B. Charles Jervas
    Charles Jervas was an Irish portrait painter and translator of Cervantes who became a prominent figure in early 18th-century London’s artistic and literary circles.
  • C. Edmund Glover
    Edmund Glover was an actor known for his role in the 1943 British mystery film "The Ghost Ship."
  • D. Giles Brindley
    Giles Brindley is a British physiologist and neuroscientist known for pioneering work in visual neuroscience and for early research on treatments for erectile dysfunction.
  • E. Nick Moorcroft
    Nick Moorcroft is a British screenwriter and film producer known for co-writing popular UK comedies such as the St Trinian’s films and Finding Your Feet.
  • 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_69d7bdf2b43c819098ae5aa68e61ea58 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96df5b68481908a5d40516b09be52 completed April 10, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8c514c481908ffff413c3873b0b completed May 3, 2026, 2:53 a.m.
Created at: April 9, 2026, 5:28 p.m.