Triple

T23207441
Position Surface form Disambiguated ID Type / Status
Subject Liv Lerner E580497 entity
Predicate hasBestFriend P27082 FINISHED
Object Emma Allan 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: Emma Allan | Statement: [Liv Lerner, hasBestFriend, Emma Allan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Allan
Context triple: [Liv Lerner, hasBestFriend, Emma Allan]
  • A. Emma Allan chosen
    Emma Allan is one of the two best friends whose relationship is tested when their weddings are accidentally scheduled on the same day in the romantic comedy film "Bride Wars."
  • B. Emily Willans
    Emily Willans was the mother of British Prime Minister Herbert Henry Asquith and a member of the Victorian-era English middle class.
  • C. Anne Wood
    Anne Wood is a British television producer best known for creating the iconic preschool series "Teletubbies."
  • D. Mary Bracegirdle
    Mary Bracegirdle is a fictional character who appears in Aldous Huxley’s novel "Crome Yellow," known for her involvement in the satirical social world surrounding Henry Wimbush.
  • E. Emily Davies
    Emily Davies was a pioneering British feminist and educational reformer who played a key role in opening university education to women in the 19th century.
  • 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_69e24602ae1481908aaa6bc7ca493867 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1907d8be08190a100d99efaff9964 completed April 29, 2026, 5 a.m.
Created at: April 17, 2026, 4:07 p.m.