Triple

T34392673
Position Surface form Disambiguated ID Type / Status
Subject Barbara Novak E882747 entity
Predicate workPublishedInStory P179381 FINISHED
Object Down with Love (book within the film) 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: Down with Love (book within the film) | Statement: [Barbara Novak, workPublishedInStory, Down with Love (book within the film)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: workPublishedInStory
Context triple: [Barbara Novak, workPublishedInStory, Down with Love (book within the film)]
  • A. workPublishedAuthor
    Indicates that a particular work was created and published by a specific author.
  • B. workPublishedBy
    Indicates that a work (such as a book, article, or other creation) has been issued or made publicly available by a particular publisher or publishing entity.
  • C. workPublishedUnderName
    Indicates that a work was released or made public using a specific name (such as a real name, pseudonym, or organizational name) as the credited author or source.
  • D. createdInWorkPublishedIn
    Indicates that something was created within a work that was subsequently published in a particular publication or venue.
  • E. selfPublished
    Indicates that an entity has published its own work independently, without an external publisher.
  • F. None of above. chosen

Provenance (4 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_69f349c1304081909331872829e38106 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f720cc1bfc8190a16118e3af8e9316 completed May 3, 2026, 10:17 a.m.
PD Predicate disambiguation batch_69f71cc6397881909aaad37a9daa8a7e completed May 3, 2026, 10 a.m.
PDg Predicate description generation batch_69f71fb0172c81908f23e95ff16b0dec completed May 3, 2026, 10:13 a.m.
Created at: May 1, 2026, 1:59 a.m.