Triple

T12120828
Position Surface form Disambiguated ID Type / Status
Subject Mount Allison University E288687 entity
Predicate hasNotableAlumni P51 FINISHED
Object Robert Ghiz
Robert Ghiz is a Canadian politician who served as the 31st Premier of Prince Edward Island from 2007 to 2015.
E962696 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: Robert Ghiz | Statement: [Mount Allison University, hasNotableAlumni, Robert Ghiz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Ghiz
Context triple: [Mount Allison University, hasNotableAlumni, Robert Ghiz]
  • A. Giorgio Jachia
    Giorgio Jachia is a mountaineer known for making the first ascent of Cassin's Ridge.
  • B. Guido De Rosso
    Guido De Rosso is an Italian former professional road cyclist known for his strong stage-race performances in the early 1960s.
  • C. Robert Marianetti
    Robert Marianetti is a filmmaker and animation director known for his work on major animated features and projects such as the Hotel Transylvania franchise.
  • D. Guido Trento
    Guido Trento was an actor known for his role in the silent film "Street Angel."
  • E. Guido Saracco
    Guido Saracco is an Italian chemical engineer and academic who serves as rector of the Polytechnic University of Turin.
  • 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: Robert Ghiz
Triple: [Mount Allison University, hasNotableAlumni, Robert Ghiz]
Generated description
Robert Ghiz is a Canadian politician who served as the 31st Premier of Prince Edward Island from 2007 to 2015.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robert Ghiz
Target entity description: Robert Ghiz is a Canadian politician who served as the 31st Premier of Prince Edward Island from 2007 to 2015.
  • A. Giorgio Jachia
    Giorgio Jachia is a mountaineer known for making the first ascent of Cassin's Ridge.
  • B. Guido De Rosso
    Guido De Rosso is an Italian former professional road cyclist known for his strong stage-race performances in the early 1960s.
  • C. Robert Marianetti
    Robert Marianetti is a filmmaker and animation director known for his work on major animated features and projects such as the Hotel Transylvania franchise.
  • D. Guido Trento
    Guido Trento was an actor known for his role in the silent film "Street Angel."
  • E. Guido Saracco
    Guido Saracco is an Italian chemical engineer and academic who serves as rector of the Polytechnic University of Turin.
  • 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_69d6ab4b5e4c81909950b17151eb0951 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d91577a03c81909add7a5d7324a648 completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f684172c81908b77daa243dc8ed8 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f5fdea1afc8190b39557fdc571e300 completed May 2, 2026, 1:36 p.m.
NED2 Entity disambiguation (via description) batch_69f5feeeeb2081908191b1c2d1c2fbfd completed May 2, 2026, 1:41 p.m.
Created at: April 8, 2026, 9:49 p.m.