Triple

T23477220
Position Surface form Disambiguated ID Type / Status
Subject Mannequin E570295 entity
Predicate title P38 FINISHED
Object Mannequin 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: Mannequin | Statement: [Mannequin, title, Mannequin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mannequin
Context triple: [Mannequin, title, Mannequin]
  • A. Mannequin chosen
    Mannequin is a 1987 romantic comedy film about a young window dresser who falls in love with a department-store mannequin that magically comes to life, starring Kim Cattrall and Andrew McCarthy.
  • B. Muñecas
    "Muñecas" is a track from the album *Kick II* by Venezuelan experimental pop artist Arca, known for her avant-garde electronic sound.
  • C. Stick Man
    Stick Man is a popular children's picture book, written by Julia Donaldson and illustrated by Axel Scheffler, about a stick figure's adventurous journey to reunite with his family.
  • D. Mannequins Dance Palace
    Mannequins Dance Palace was a popular, high-energy nightclub at Disney’s Pleasure Island known for its rotating dance floor and cutting-edge music and lighting.
  • E. Manne
    Manne is a given name most notably borne by Swedish physicist Manne Siegbahn, a Nobel laureate recognized for his work in X-ray spectroscopy.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a74dbea8819085ca84391039e7f7 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:01 p.m.