Triple

T19918265
Position Surface form Disambiguated ID Type / Status
Subject Moxyland E478720 entity
Predicate publisher P29 FINISHED
Object Angry Robot 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: Angry Robot | Statement: [Moxyland, publisher, Angry Robot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angry Robot
Context triple: [Moxyland, publisher, Angry Robot]
  • A. Angry Robot chosen
    Angry Robot is a British science fiction and fantasy publishing imprint known for releasing innovative and genre-bending speculative fiction.
  • B. Citadel Press
    Citadel Press is a publishing company known for producing popular nonfiction works, including influential historical and reference titles.
  • C. Dark Horse Books
    Dark Horse Books is a publishing imprint of Dark Horse Comics known for releasing graphic novels, comic collections, and related prose works.
  • D. Firebrand Books
    Firebrand Books is a pioneering feminist and lesbian publishing house known for championing queer literature and progressive political works.
  • E. Persephone Books
    Persephone Books is an independent British publishing house renowned for reprinting neglected or out-of-print works, particularly by mid-20th-century women writers, in distinctive grey-covered editions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659c3d990819089386d9f30323e8c completed April 20, 2026, 4:52 p.m.
Created at: April 10, 2026, 1:53 p.m.