Triple

T22079284
Position Surface form Disambiguated ID Type / Status
Subject Elisabeth Holm E545603 entity
Predicate notableWork P4 FINISHED
Object Landline 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: Landline | Statement: [Elisabeth Holm, notableWork, Landline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Landline
Context triple: [Elisabeth Holm, notableWork, Landline]
  • A. Landline chosen
    Landline is a 2017 American comedy-drama film set in 1990s New York City that follows a family dealing with infidelity and personal upheaval, starring Jenny Slate.
  • B. Coldline
    Coldline is a Google Cloud Storage class designed for low-cost, long-term storage of infrequently accessed data with higher retrieval latency and fees.
  • C. Telefon Bay
    Telefon Bay is a small volcanic bay on Deception Island in Antarctica, known for its stark polar landscape and evidence of past eruptions.
  • D. Loveline
    Loveline is a long-running American radio call-in show, later adapted for television, that focused on relationships, sex, and health advice, famously co-hosted by Adam Carolla and Dr. Drew Pinsky.
  • E. Landline Green
    Landline Green is a notable artwork from the Landline series, characterized by its layered horizontal bands of color that evoke landscapes and horizons.
  • 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_69e11e3523488190badd54b5d580c00d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b43df0819090c248ded98fad12 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.