Triple

T10776689
Position Surface form Disambiguated ID Type / Status
Subject Zelig E254214 entity
Predicate title P38 FINISHED
Object Zelig E254214 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: Zelig | Statement: [Zelig, title, Zelig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zelig
Context triple: [Zelig, title, Zelig]
  • A. Zelig chosen
    Zelig is a 1983 mockumentary-style comedy film by Woody Allen about a human chameleon who miraculously adapts his appearance and personality to fit in with those around him.
  • B. 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.
  • C. The King of Comedy
    The King of Comedy is a 1982 dark comedy film directed by Martin Scorsese that satirizes celebrity culture through the story of an obsessive aspiring comedian.
  • D. The King of Comedy
    The King of Comedy is a nickname for Jerry Lewis, the influential American comedian, actor, and filmmaker renowned for his slapstick humor and pioneering work in comedy.
  • E. The Purple Rose of Cairo
    The Purple Rose of Cairo is a 1985 fantasy-romantic comedy film written and directed by Woody Allen about a movie character who steps off the screen into the real world during the Great Depression.
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7329d8c908190bddad40685133ea1 completed April 9, 2026, 5:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69de238ff88881908676d38dca041cb4 completed April 14, 2026, 11:22 a.m.
Created at: April 8, 2026, 9:16 p.m.