Triple

T8154749
Position Surface form Disambiguated ID Type / Status
Subject Geraldine Granger E190416 entity
Predicate broadcastMediumOfWork P17106 FINISHED
Object television 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: television | Statement: [Geraldine Granger, broadcastMediumOfWork, television]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: broadcastMediumOfWork
Context triple: [Geraldine Granger, broadcastMediumOfWork, television]
  • A. broadcastVia chosen
    Indicates that an action, message, or content is transmitted or disseminated through a specified medium, channel, or platform.
  • B. broadcastFor
    Indicates that one entity transmits or disseminates content, information, or a signal on behalf of, or in service of, another entity.
  • C. broadcastType
    Indicates the specific mode or category of broadcasting used to transmit content (e.g., live, recorded, streaming, or other broadcast formats) between entities.
  • D. broadcastModel
    Indicates that one entity serves as the template or source whose structure or values are replicated and applied across another entity or set of entities.
  • E. broadcastFrom
    Indicates that some content, signal, or message is transmitted or emitted starting at a particular source location, device, or entity.
  • 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb44d725b88190b77dc7537c1fa95d completed March 31, 2026, 3:51 a.m.
PD Predicate disambiguation batch_69cb36a0847c8190af9038aef78319b3 completed March 31, 2026, 2:51 a.m.
Created at: March 30, 2026, 5:37 p.m.