Triple

T17990830
Position Surface form Disambiguated ID Type / Status
Subject Flickering Lights E430364 entity
Predicate cinematographyBy P1953 FINISHED
Object Eric Kress 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: Eric Kress | Statement: [Flickering Lights, cinematographyBy, Eric Kress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eric Kress
Context triple: [Flickering Lights, cinematographyBy, Eric Kress]
  • A. Eric Kress chosen
    Eric Kress is a Danish cinematographer known for his visually distinctive work on international films, including genre-bending projects like "Colossal."
  • B. Mike Kellerman
    Mike Kellerman is a fictional Baltimore homicide detective known for his morally complex investigations and personal struggles on the television series "Homicide: Life on the Street."
  • C. Eric Klieg
    Eric Klieg is a human villain from the Doctor Who universe, known for his role in the Second Doctor serial "The Tomb of the Cybermen."
  • D. Mitch Kertzman
    Mitch Kertzman is an American technology executive and entrepreneur best known for his leadership roles in the software and semiconductor industries, including at companies like LSI Logic and Sybase.
  • E. Brian Kessler
    Brian Kessler is a young writer and true-crime enthusiast who embarks on a cross-country road trip to research serial killers in the film "Kalifornia."
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29f127c81908b0c4cb3787e002c completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.