Triple

T37767325
Position Surface form Disambiguated ID Type / Status
Subject Annegret Kramp-Karrenbauer E941449 entity
Predicate precededByAsMinisterPresidentOfSaarland P196165 FINISHED
Object Peter Müller
Peter Müller is a German politician and former Minister-President of the state of Saarland.
E2244466 NE FINISHED

How this triple was built (3 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: Peter Müller | Statement: [Annegret Kramp-Karrenbauer, precededByAsMinisterPresidentOfSaarland, Peter Müller]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Peter Müller
Triple: [Annegret Kramp-Karrenbauer, precededByAsMinisterPresidentOfSaarland, Peter Müller]
Generated description
Peter Müller is a German politician and former Minister-President of the state of Saarland.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: precededByAsMinisterPresidentOfSaarland
Context triple: [Annegret Kramp-Karrenbauer, precededByAsMinisterPresidentOfSaarland, Peter Müller]
  • A. precededBy (as Minister-President of Lower Saxony)
    Indicates that one individual previously held the position of Minister-President of Lower Saxony before another individual, establishing a direct succession in that office.
  • B. formerChancellor
    Indicates that one entity previously held the position or role of chancellor of the other entity, but no longer does.
  • C. precededInOfficeAsChancellorBy
    Indicates that one individual assumed the role of Chancellor after another specific individual, who held the office immediately before them.
  • D. precededByAsChiefMinister
    Indicates that one individual previously served as chief minister before another individual in a sequence of officeholders.
  • E. succeededBy (as Minister-President of Lower Saxony)
    Indicates that one individual later took over the role of Minister-President of Lower Saxony from another individual, becoming their direct successor in that office.
  • F. None of above. chosen

Provenance (7 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_69f76ee3251881909bb4451aad50752b completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fe0d165a48819098b854318a50d76c completed May 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40f17afeec81908309e8019fe480c3 completed June 28, 2026, 10:03 a.m.
NEDg Description generation batch_6a40f286b12c8190a2a2b49b6711e7e5 completed June 28, 2026, 10:08 a.m.
NED2 Entity disambiguation (via description) batch_6a40f3fe400c8190a8ea39d67b33c0c8 completed June 28, 2026, 10:14 a.m.
PD Predicate disambiguation batch_69fe0931002481908a95b34f95e9f64e completed May 8, 2026, 4:02 p.m.
PDg Predicate description generation batch_69fe0d14778c8190986fa4f37f992a2f completed May 8, 2026, 4:19 p.m.
Created at: May 3, 2026, 4:19 p.m.