Triple

T18262186
Position Surface form Disambiguated ID Type / Status
Subject Mrs. Harling E437384 entity
Predicate marriedTo P13 FINISHED
Object Mr. Harling 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: Mr. Harling | Statement: [Mrs. Harling, marriedTo, Mr. Harling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mr. Harling
Context triple: [Mrs. Harling, marriedTo, Mr. Harling]
  • A. Mr. Harling chosen
    Mr. Harling is a prosperous, energetic merchant and the head of the Harling family in Willa Cather’s novel "My Ántonia," known for his strict yet fundamentally kind-hearted nature.
  • B. Harold Turpin
    Harold Turpin is an alias used by Harold Finch, the reclusive billionaire software genius from the TV series "Person of Interest."
  • C. Mr. Lloyd
    Mr. Lloyd is a character in the film "The Wedding Party," contributing to the story’s ensemble of wedding guests and their intertwined relationships.
  • D. Harold Tennant
    Harold Tennant was a British Liberal politician and government minister in the early 20th century, associated with the administration of H. H. Asquith.
  • E. Mr. Hall
    Mr. Hall is a character in the stage musical "Clueless," portrayed as a well-meaning but strict high school teacher who becomes the target of a matchmaking scheme.
  • 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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ff76a1208190abbe6ab8720ed154 completed April 19, 2026, 4:14 p.m.
Created at: April 10, 2026, 10:34 a.m.