Triple

T19789467
Position Surface form Disambiguated ID Type / Status
Subject Donna Logan E475370 entity
Predicate relative P37 FINISHED
Object Hope Logan NE NERFINISHED

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: Hope Logan | Statement: [Donna Logan, relative, Hope Logan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hope Logan
Context triple: [Donna Logan, relative, Hope Logan]
  • A. Hope Logan chosen
    Hope Logan is a central fictional character on the American soap opera "The Bold and the Beautiful," known for her complex romantic entanglements and role in the Logan family drama.
  • B. Logan Walker
    Logan Walker is the silent protagonist and playable main character in the first-person shooter video game Call of Duty: Ghosts.
  • C. Logan Coles
    Logan Coles is a film producer best known for collaborating with Chadwick Boseman on projects such as the crime thriller "21 Bridges."
  • D. Logan Storley
    Logan Storley is an American mixed martial artist and accomplished collegiate wrestler who competes as a top contender in Bellator’s welterweight division.
  • E. Logan Williamson
    Logan Williamson is the twin sibling of New Zealand international cricketer Kane Williamson.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6538ae5108190b80eb7de6f445f02 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.