Triple

T7977105
Position Surface form Disambiguated ID Type / Status
Subject Stewart Butterfield E185473 entity
Predicate employer P7 FINISHED
Object Ludicorp E703155 NE 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: Ludicorp | Statement: [Stewart Butterfield, employer, Ludicorp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludicorp
Context triple: [Stewart Butterfield, employer, Ludicorp]
  • A. Ludicorp chosen
    Ludicorp was a Canadian software company best known for creating the photo-sharing service Flickr before being acquired by Yahoo.
  • B. Creatures Inc.
    Creatures Inc. is a Japanese video game development company best known for its key role in creating and managing the Pokémon franchise’s games, cards, and related media.
  • C. Kopelson Entertainment
    Kopelson Entertainment is a film and television production company best known for producing high-profile Hollywood action and thriller movies.
  • D. Wolf Entertainment
    Wolf Entertainment is an American television production company founded by producer Dick Wolf, best known for creating and overseeing the long-running Law & Order and Chicago franchise series.
  • E. Chameleon Entertainment
    Chameleon Entertainment is a music record label known for producing and distributing recordings for various artists across genres.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca829851908190b4e03829353ee7c3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3bf716508190b4245bd5d89ae8c4 completed March 31, 2026, 3:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc5677968881908835169157244962 completed March 31, 2026, 11:19 p.m.
Created at: March 30, 2026, 5:14 p.m.