Triple

T35332099
Position Surface form Disambiguated ID Type / Status
Subject Margrave of Austria E1020347 entity
Predicate firstMargrave P84512 FINISHED
Object Leopold I, Margrave of Austria E1175772 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: Leopold I, Margrave of Austria | Statement: [Margrave of Austria, firstMargrave, Leopold I, Margrave of Austria]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: firstMargrave
Context triple: [Margrave of Austria, firstMargrave, Leopold I, Margrave of Austria]
  • A. firstGrandDuke
    Indicates that the subject is the first person to hold the title or position of grand duke of the specified entity.
  • B. predecessorAsLandgraveOfThuringia
    Indicates that one entity held the position of Landgrave of Thuringia immediately before another entity, serving as that successor’s predecessor in this title.
  • C. firstDespot chosen
    Indicates that the subject is the earliest or original ruler with despotic authority over the object (such as a state, territory, or people).
  • D. successorInLotharingia
    Indicates that one entity is the direct successor of another in ruling or holding authority over Lotharingia.
  • E. predecessorAsKingOfEastFrancia
    Indicates that one person previously held the position of King of East Francia immediately before another person.
  • F. None of above.

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_69f76deacf4481908e7735a5a7715b0a completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_6a037c8c34f88190ace26f555827f23e completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3836a213148190977da648647d86bc completed June 21, 2026, 7:08 p.m.
PD Predicate disambiguation batch_6a037a0324d08190ac5b610cc0f6a38c completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:03 p.m.