Triple

T29074183
Position Surface form Disambiguated ID Type / Status
Subject Judgment Night E735890 entity
Predicate associatedGenrePublisher P203977 FINISHED
Object Gnome Press E200986 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: Gnome Press | Statement: [Judgment Night, associatedGenrePublisher, Gnome Press]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedGenrePublisher
Context triple: [Judgment Night, associatedGenrePublisher, Gnome Press]
  • A. publishedGenre
    Indicates that an entity has been published in, or is associated with, a particular genre.
  • B. publisherType
    Indicates the classification or category of a publisher in relation to a published work or entity.
  • C. publisherAssociatedWith
    Indicates a relationship where a publisher is connected or linked to another entity, such as by publishing, distributing, or otherwise being involved with its content or materials.
  • D. publisherWorkedWith
    Indicates that a publisher has collaborated or engaged in a professional working relationship with another party (such as an author, organization, or creator).
  • E. publisherOfWorkFeaturing
    Indicates that one entity serves as the publisher responsible for releasing or distributing a work in which another specified entity is featured.
  • F. None of above. chosen

Provenance (5 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_69f077e9b0a48190bb79548279cb7f64 completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_6a0303622ce08190b359c9d247268729 completed May 12, 2026, 10:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a25504bd4ec8190b0087063558d6eb0 completed June 7, 2026, 11:04 a.m.
PD Predicate disambiguation batch_6a03030c02fc81908e546dba291b1240 completed May 12, 2026, 10:38 a.m.
PDg Predicate description generation batch_6a03036152e4819082881a9f59919e1b completed May 12, 2026, 10:39 a.m.
Created at: April 28, 2026, 10:22 a.m.