Triple

T24864133
Position Surface form Disambiguated ID Type / Status
Subject Kniephof E622233 entity
Predicate historicalOwnership P22003 FINISHED
Object Mencken family 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: Mencken family | Statement: [Kniephof, historicalOwnership, Mencken family]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: historicalOwnership
Context triple: [Kniephof, historicalOwnership, Mencken family]
  • A. ownershipHistory chosen
    Indicates the sequence of past and present owners associated with an entity over time.
  • B. previouslyPossessedBy
    Indicates that an entity was owned or possessed by another entity at some time in the past, but is not necessarily possessed by that entity now.
  • C. ownershipSince
    Indicates the point in time from which an entity has continuously owned another entity.
  • D. ownershipRecordedBy
    Indicates that the fact or status of ownership of an entity is documented or registered by a particular agent or system.
  • E. ownershipRecord
    Indicates that there exists a documented relationship specifying which entity legally owns or possesses another entity, typically including details such as owner, owned item, and relevant terms or period of ownership.
  • F. None of above.

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_69e2fac350d08190b3affde1b451a8c5 completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f657f653448190a945b4751af8507d completed May 2, 2026, 8 p.m.
PD Predicate disambiguation batch_69f6575ba12081909396036f78757a76 completed May 2, 2026, 7:58 p.m.
Created at: April 18, 2026, 5:22 a.m.