Triple

T33604560
Position Surface form Disambiguated ID Type / Status
Subject Walter Haut E860812 entity
Predicate hasPartInWrittenWork P199560 FINISHED
Object Roswell incident affidavits LITERAL 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: Roswell incident affidavits | Statement: [Walter Haut, hasPartInWrittenWork, Roswell incident affidavits]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasPartInWrittenWork
Context triple: [Walter Haut, hasPartInWrittenWork, Roswell incident affidavits]
  • A. hasPartInCreativeOutput
    Indicates that an entity contributed a component, role, or involvement to the creation or production of a particular creative work.
  • B. appearsInWorkWrittenBy
    Indicates that an entity is featured or occurs within a work that was authored by a specified creator.
  • C. attestedInWorksOf
    Indicates that something (such as a claim, form, or usage) is documented or evidenced within the works produced by a particular author or creator.
  • D. isPartOfBodyOfWork
    Indicates that one creative work is a component, segment, or installment within a larger overarching body of related work.
  • E. hasAssociatedWorkOfFiction
    Indicates that an entity is linked to a related work of fiction, such as a novel, film, or story that is associated with it.
  • 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_69f3498037c88190a4500f002b5540e0 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69ff45793d5c81909dc503ad1f714ee2 completed May 9, 2026, 2:32 p.m.
PD Predicate disambiguation batch_69ff41cb0e088190a6e9b03cb20e5fad completed May 9, 2026, 2:16 p.m.
PDg Predicate description generation batch_69ff45782cb88190b604811e4d724382 completed May 9, 2026, 2:32 p.m.
Created at: May 1, 2026, 1:41 a.m.