Triple

T16569865
Position Surface form Disambiguated ID Type / Status
Subject Duc de Magenta E402555 entity
Predicate titleHolderRankAttainedYear P18619 FINISHED
Object Marshal of France 1859 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: Marshal of France 1859 | Statement: [Duc de Magenta, titleHolderRankAttainedYear, Marshal of France 1859]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: titleHolderRankAttainedYear
Context triple: [Duc de Magenta, titleHolderRankAttainedYear, Marshal of France 1859]
  • A. titleHolderRank chosen
    Indicates the relative position or level of precedence assigned to a title holder within a ranked order or hierarchy.
  • B. titleHolderSince
    Indicates the entity that has held a particular title or position continuously from a specified starting time.
  • C. lastHolderRank
    Indicates the rank or position held by the most recent entity that possessed or held a given item, title, or role.
  • D. earliestKnownHolder
    Indicates that the subject is the first known entity in time to have possessed, held, or been assigned the object.
  • E. recordHolderMostTitles
    Indicates that one entity holds the highest number of titles (e.g., championships, awards, or similar distinctions) compared to all other entities in a given context.
  • 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_69d8838648088190acf97ef11fc3f61b completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e359580f548190a21afd148bc22d8d completed April 18, 2026, 10:13 a.m.
PD Predicate disambiguation batch_69e296a47b7481909d9958158510c806 completed April 17, 2026, 8:23 p.m.
Created at: April 10, 2026, 5:16 a.m.