Triple

T8996806
Position Surface form Disambiguated ID Type / Status
Subject Collapse E214936 entity
Predicate publisher P29 FINISHED
Object Viking Press E60544 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: Viking Press | Statement: [Collapse, publisher, Viking Press]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viking Press
Context triple: [Collapse, publisher, Viking Press]
  • A. The Viking Press chosen
    The Viking Press is an American publishing company known for releasing influential literary works by prominent authors throughout the 20th century.
  • B. World Publishing Company
    World Publishing Company was a prominent American book publisher known for producing a wide range of trade and literary titles in the mid-20th century.
  • C. Harper & Row
    Harper & Row was a major American publishing house known for producing influential works in literature, education, and academic scholarship.
  • D. Appleton-Century
    Appleton-Century was an American publishing company known for producing influential academic and scientific works in the early to mid-20th century.
  • E. Abingdon Press
    Abingdon Press is a major Christian publishing house associated with the United Methodist Church, known for producing worship resources, theological works, and religious educational materials.
  • 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_69ca83a05c608190bdfdbdb25e994b39 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc68df33c48190a5017426e59c0bc4 completed April 1, 2026, 12:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0d586c881909090b424f6fd036f completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:05 p.m.