Triple

T22829838
Position Surface form Disambiguated ID Type / Status
Subject Robert Ellsberg E565767 entity
Predicate employer P7 FINISHED
Object Orbis Books 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: Orbis Books | Statement: [Robert Ellsberg, employer, Orbis Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orbis Books
Context triple: [Robert Ellsberg, employer, Orbis Books]
  • A. Orbis Books chosen
    Orbis Books is a Catholic publishing house known for progressive and liberation theology titles that engage issues of social justice and faith.
  • B. Orbit Books
    Orbit Books is a major science fiction and fantasy publishing imprint known for releasing works by prominent genre authors worldwide.
  • C. Pinnacle Books
    Pinnacle Books was an American paperback publisher known for releasing genre fiction, including science fiction titles such as issues or collections associated with Galaxy Science Fiction.
  • D. Hyperion Books
    Hyperion Books is an American publishing imprint, originally founded by The Walt Disney Company, known for releasing a wide range of popular fiction and non-fiction titles.
  • E. Harmony Books
    Harmony Books is a publishing imprint known for releasing a range of popular nonfiction and literary titles, including works in science, culture, and contemporary thought.
  • 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_69e24585ab1c81909b2b5065d15805d5 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e2ac8d48190b6dc7edc5ad82bc7 completed April 29, 2026, 3:42 a.m.
Created at: April 17, 2026, 3:34 p.m.