Triple

T18262159
Position Surface form Disambiguated ID Type / Status
Subject Mr. Harling E437383 entity
Predicate hasChild P369 FINISHED
Object Nina 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: Nina Harling | Statement: [Mr. Harling, hasChild, Nina Harling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nina Harling
Context triple: [Mr. Harling, hasChild, Nina Harling]
  • A. Julia Harling chosen
    Julia Harling is an individual known primarily as the child of Mr. Harling.
  • B. Nina Reeves
    Nina Reeves is a complex and often controversial magazine publisher and socialite on the soap opera "General Hospital," known for her tumultuous relationships and dramatic storylines.
  • C. Nina Locke
    Nina Locke is a central character in the horror-fantasy comic and TV series "Locke & Key," known as the widowed mother who moves her family into the mysterious Keyhouse after a tragic loss.
  • D. Nina Jones
    Nina Jones is a character from the Nickelodeon live-action sitcom "Cousin Skeeter," which follows the misadventures of a wisecracking puppet and his human family.
  • E. Nina King
    Nina King is an American college athletics administrator who serves as the athletic director at Duke University, overseeing the university’s sports programs.
  • 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.