Triple

T30813843
Position Surface form Disambiguated ID Type / Status
Subject Christopher James Berman E784718 entity
Predicate worksForNetwork P5820 FINISHED
Object ESPN 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: ESPN | Statement: [Christopher James Berman, worksForNetwork, ESPN]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: worksForNetwork
Context triple: [Christopher James Berman, worksForNetwork, ESPN]
  • A. workOnNetwork
    Indicates that an entity is engaged in building, maintaining, or operating a network or network-related infrastructure.
  • B. worksFor chosen
    Indicates that one entity is employed by or performs work on behalf of another entity, typically an organization or individual.
  • C. supportedNetwork
    Indicates that one entity (such as a device, service, or application) is compatible with, operates on, or is designed to work over a specified network or type of network.
  • D. netWork
    Indicates a relationship where entities are connected or interact within a shared system, structure, or set of links that enables communication or exchange.
  • E. operatesNetwork
    Indicates that an entity manages, controls, or runs the functioning of a network.
  • 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_69f224b4eda48190bd212ce4f3901e56 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f73223675481908c1bc3208c0f5284 completed May 3, 2026, 11:31 a.m.
PD Predicate disambiguation batch_69f7317690108190b3aae2cd2e1d069e completed May 3, 2026, 11:28 a.m.
Created at: April 29, 2026, 8:43 p.m.