Triple

T16854844
Position Surface form Disambiguated ID Type / Status
Subject Path of Illumination E409756 entity
Predicate filmAdaptationChanges P125243 FINISHED
Object route and locations altered for cinematic purposes LITERAL 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: route and locations altered for cinematic purposes | Statement: [Path of Illumination, filmAdaptationChanges, route and locations altered for cinematic purposes]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: filmAdaptationChanges
Context triple: [Path of Illumination, filmAdaptationChanges, route and locations altered for cinematic purposes]
  • A. inFilmAdaptation
    Indicates that one work or element appears within, or is incorporated into, a film adaptation of another work.
  • B. fromFilmAdaptation
    Indicates that something originates from, or is derived from, a film adaptation of another work.
  • C. filmAdaptationFormat
    Indicates the specific medium or format (e.g., feature film, TV movie, short film) in which a work has been adapted into a film.
  • D. filmAdaptationOfLife
    Indicates that a film is an adaptation based on the life or real-life experiences of a person or group.
  • E. laterAdaptedFor
    Indicates that something was subsequently modified or repurposed to serve a new use, context, or medium.
  • F. None of above. chosen

Provenance (4 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b37c6e808190975b14b228253029 completed April 18, 2026, 4:38 p.m.
PD Predicate disambiguation batch_69e32b8cbb048190878a259cc5be960e completed April 18, 2026, 6:58 a.m.
PDg Predicate description generation batch_69e355722040819098830dabf207ecd6 completed April 18, 2026, 9:57 a.m.
Created at: April 10, 2026, 5:24 a.m.