Triple

T31754030
Position Surface form Disambiguated ID Type / Status
Subject Coral E810507 entity
Predicate onScreenTime P62983 FINISHED
Object opening sequence of Finding Nemo 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: opening sequence of Finding Nemo | Statement: [Coral, onScreenTime, opening sequence of Finding Nemo]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: onScreenTime
Context triple: [Coral, onScreenTime, opening sequence of Finding Nemo]
  • A. screenTime
    Indicates the amount of time an entity spends viewing or interacting with a screen-based device.
  • B. screenTimeProportion
    Indicates the proportion of total time that an entity spends looking at or using a screen relative to a defined overall time period.
  • C. hasScreenTimeIn chosen
    Indicates that an entity appears on screen for a certain duration within a specified audiovisual work or segment.
  • D. screenTimeFunction
    Indicates a functional relationship that maps an entity (such as a user, device, or app) to the amount of time its screen is active or in use.
  • E. screenTimeFocus
    Indicates the amount or proportion of time an entity’s attention or activity is concentrated on a particular screen or digital display.
  • F. None of above.

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_69f348e340d48190b780fae618c51464 completed April 30, 2026, 12:19 p.m.
NER Named-entity recognition batch_69f6ab7a9a408190a227d66d8c1a55f3 completed May 3, 2026, 1:57 a.m.
PD Predicate disambiguation batch_69f6aa20a1588190a53533fc9764efb2 completed May 3, 2026, 1:51 a.m.
Created at: April 30, 2026, 11:29 p.m.