Triple

T14736582
Position Surface form Disambiguated ID Type / Status
Subject Isabel Preysler E346224 entity
Predicate parent P120 FINISHED
Object Carlos Preysler
Carlos Preysler is a member of the prominent Spanish-Philippine Preysler family, known primarily as one of Isabel Preysler’s children.
E1122873 NE FINISHED

How this triple was built (4 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: Carlos Preysler | Statement: [Isabel Preysler, parent, Carlos Preysler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carlos Preysler
Context triple: [Isabel Preysler, parent, Carlos Preysler]
  • A. Paul Krendler
    Paul Krendler is a corrupt and antagonistic U.S. Justice Department official who serves as a key foil to Clarice Starling in the film "Hannibal."
  • B. Paul Knabenshue
    Paul Knabenshue was an American diplomat best known for serving as the first U.S. Ambassador to Iraq in the early 20th century.
  • C. Michael Breyer
    Michael Breyer is the son of former U.S. Supreme Court Justice Stephen G. Breyer.
  • D. George Kralovansky
    George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
  • E. Peter Riedler
    Peter Riedler is an Austrian academic and university administrator who serves as rector of the University of Graz.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Carlos Preysler
Triple: [Isabel Preysler, parent, Carlos Preysler]
Generated description
Carlos Preysler is a member of the prominent Spanish-Philippine Preysler family, known primarily as one of Isabel Preysler’s children.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carlos Preysler
Target entity description: Carlos Preysler is a member of the prominent Spanish-Philippine Preysler family, known primarily as one of Isabel Preysler’s children.
  • A. Paul Krendler
    Paul Krendler is a corrupt and antagonistic U.S. Justice Department official who serves as a key foil to Clarice Starling in the film "Hannibal."
  • B. Paul Knabenshue
    Paul Knabenshue was an American diplomat best known for serving as the first U.S. Ambassador to Iraq in the early 20th century.
  • C. Michael Breyer
    Michael Breyer is the son of former U.S. Supreme Court Justice Stephen G. Breyer.
  • D. George Kralovansky
    George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
  • E. Peter Riedler
    Peter Riedler is an Austrian academic and university administrator who serves as rector of the University of Graz.
  • F. None of above. chosen

Provenance (5 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec73114cc819088e1101b689fc70b completed April 14, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe388792688190b1b6eaa8091733fb completed May 8, 2026, 7:24 p.m.
NEDg Description generation batch_69fe51eab88481908db2bca9bf6d60ec completed May 8, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_69fe525438f88190aa88e68e1395a20b completed May 8, 2026, 9:15 p.m.
Created at: April 10, 2026, 1:29 a.m.