Triple

T17322857
Position Surface form Disambiguated ID Type / Status
Subject Landgraf E420603 entity
Predicate mayBeVassalOf P7255 FINISHED
Object Duke 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: Duke | Statement: [Landgraf, mayBeVassalOf, Duke]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mayBeVassalOf
Context triple: [Landgraf, mayBeVassalOf, Duke]
  • A. vassalsOf chosen
    Indicates that one entity serves as a subordinate or dependent vassal under the authority or suzerainty of another entity.
  • B. vassalageOver
    Indicates a hierarchical feudal relationship in which one party is a vassal subordinate to and owing allegiance or obligations to another.
  • C. vassalageConcerned
    Indicates that one entity is concerned with, or involved in matters related to, the vassalage status or obligations of another entity.
  • D. vassalageStart
    Indicates the point in time when a vassalage relationship—where one party becomes subordinate or owes allegiance to another—officially begins.
  • E. vassalState
    Indicates a relationship where one political entity is subordinate to and under the authority or control of another, typically more powerful, state.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e439d01e2c8190a358dace420d4575 completed April 19, 2026, 2:11 a.m.
PD Predicate disambiguation batch_69e3b01b9d1c8190a406dd941c9b11a1 completed April 18, 2026, 4:23 p.m.
Created at: April 10, 2026, 5:43 a.m.