Triple

T21480966
Position Surface form Disambiguated ID Type / Status
Subject Marnie Piper E529990 entity
Predicate sibling P363 FINISHED
Object Sophie Piper 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: Sophie Piper | Statement: [Marnie Piper, sibling, Sophie Piper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sophie Piper
Context triple: [Marnie Piper, sibling, Sophie Piper]
  • A. Sophie Piper chosen
    Sophie Piper is the youngest Cromwell sibling in Disney's "Halloweentown" film series, known for her emerging magical abilities and intuitive connection to the supernatural.
  • B. Sophie Piper
    Sophie Piper was a Swedish noblewoman and courtier of the late 18th and early 19th centuries, known for her close ties to the royal court and involvement in contemporary political and social circles.
  • C. Sophie Baker
    Sophie Baker is known as the wife of acclaimed English actor Ian Holm.
  • D. Sophie Baker
    Sophie Baker is the charming and seemingly clairvoyant young spiritualist portrayed by Emma Stone in Woody Allen’s romantic comedy film "Magic in the Moonlight."
  • E. Sophie Morgan
    Sophie Morgan is a British television presenter, disability rights advocate, and artist known for her work on inclusive media and representation of disabled people.
  • 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_69e0c45acc3881908e38d3f28964152b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea338f988190a3044f8d02a567fe completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:21 p.m.