Triple

T18959140
Position Surface form Disambiguated ID Type / Status
Subject At War with the Army E463861 entity
Predicate follows P134 FINISHED
Object My Friend Irma 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: My Friend Irma | Statement: [At War with the Army, follows, My Friend Irma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: My Friend Irma
Context triple: [At War with the Army, follows, My Friend Irma]
  • A. My Friend Irma chosen
    My Friend Irma is a popular mid-20th-century American comedy franchise, best known as a radio and film series about a scatterbrained young woman and her friends.
  • B. My Friend Irma Goes West
    My Friend Irma Goes West is a 1950 American comedy film and sequel to My Friend Irma, featuring the characters Irma and Jane in a Hollywood-set misadventure.
  • C. Our Friend
    Our Friend is a 2019 drama film based on a true story, following a couple facing terminal illness and the selfless friend who moves in to support them and their family.
  • D. Faces of Jim
    Faces of Jim is a British television comedy series co-written by humorist Frank Muir, featuring character-based sketches and situational humor.
  • E. Irma Vep
    Irma Vep is a French-American television miniseries that blends meta-cinema, crime, and dark comedy as it follows an actress remaking a classic silent-era vampire serial.
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5d057a48190b82b5788b3281e28 completed April 20, 2026, 7:29 a.m.
Created at: April 10, 2026, noon