Triple

T5129332
Position Surface form Disambiguated ID Type / Status
Subject Joseph Joffre E115656 entity
Predicate promotedToMarshalOfFrance P62781 FINISHED
Object 1916 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: 1916 | Statement: [Joseph Joffre, promotedToMarshalOfFrance, 1916]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: promotedToMarshalOfFrance
Context triple: [Joseph Joffre, promotedToMarshalOfFrance, 1916]
  • A. promotedToMajorGeneralOfVolunteers
    Indicates that a person was elevated in rank to serve as a major general within a volunteer military force.
  • B. isOldestMilitaryDecorationOf
    Indicates that one military decoration is the earliest or first established award within a specified group, organization, or country.
  • C. isMilitaryDecorationOf
    Indicates that something is a military award or honor that has been conferred upon a particular person, unit, or entity.
  • D. militaryAward
    Indicates that an entity has received or been granted a specific military honor, decoration, or award.
  • E. successorAsEmpressOfTheFrench
    Indicates that one person became the next Empress of the French following another person in that imperial role.
  • 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7fef2e8c8190982dd67f50295ada completed March 20, 2026, 5:12 p.m.
PD Predicate disambiguation batch_69bd77ac2fc48190abeebb003a82384c completed March 20, 2026, 4:37 p.m.
PDg Predicate description generation batch_69bd7fee42748190967013828973cce0 completed March 20, 2026, 5:12 p.m.
Created at: March 20, 2026, 1:42 p.m.