Triple

T14815470
Position Surface form Disambiguated ID Type / Status
Subject Constance Bennett E348300 entity
Predicate notableWork P4 FINISHED
Object Topper E175888 NE FINISHED

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: Topper | Statement: [Constance Bennett, notableWork, Topper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Topper
Context triple: [Constance Bennett, notableWork, Topper]
  • A. Topper (film series) chosen
    Topper is a classic American comedy film series from the late 1930s and early 1940s, centered on a stuffy banker whose life is upended by the mischievous ghosts of a fun-loving couple.
  • B. Pop-Pop
    Pop-Pop is the affectionate family nickname for George Bluth Sr., the scheming patriarch from the television series "Arrested Development."
  • C. Tip Top House
    Tip Top House is a historic stone hotel and former summit house located atop Mount Washington in New Hampshire, known as one of the oldest surviving mountain-top hostels in the United States.
  • D. The Mister
    The Mister is a contemporary romance novel by E. L. James, known for its Cinderella-style love story and for being her follow-up to the Fifty Shades series.
  • E. Tootsie
    Tootsie is a 1982 American comedy film in which Dustin Hoffman plays an out-of-work actor who disguises himself as a woman to land a role, leading to unexpected fame and complications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe0e89c81908c0e1fe2bc3ebcfc completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389598848190ba15e6eea2ba2903 completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:49 a.m.