Triple

T10781616
Position Surface form Disambiguated ID Type / Status
Subject Treasurer of Western Australia E254330 entity
Predicate officeHoldersInclude P537 FINISHED
Object Frank Wise
Frank Wise was an Australian politician who served as Premier of Western Australia in the 1940s and later held senior roles in public administration.
E886425 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: Frank Wise | Statement: [Treasurer of Western Australia, officeHoldersInclude, Frank Wise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Wise
Context triple: [Treasurer of Western Australia, officeHoldersInclude, Frank Wise]
  • A. Raymond Wise
    Raymond Wise is a name shared by multiple individuals, most notably an American actor recognized for his roles in film and television.
  • B. Jerry Wisdom
    Jerry Wisdom was a Bahamian sprinter known for competing in international track and field events, including the Olympic Games.
  • C. Jack Wisdom
    Jack Wisdom is an American planetary scientist and MIT professor known for his work on celestial mechanics and dynamical chaos in the solar system.
  • D. Herbert Wise
    Herbert Wise was a British television and film director best known for his acclaimed work on period dramas and literary adaptations.
  • E. William Wise
    William Wise is an actor known for his role in the acclaimed drama film "In the Bedroom."
  • 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: Frank Wise
Triple: [Treasurer of Western Australia, officeHoldersInclude, Frank Wise]
Generated description
Frank Wise was an Australian politician who served as Premier of Western Australia in the 1940s and later held senior roles in public administration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frank Wise
Target entity description: Frank Wise was an Australian politician who served as Premier of Western Australia in the 1940s and later held senior roles in public administration.
  • A. Raymond Wise
    Raymond Wise is a name shared by multiple individuals, most notably an American actor recognized for his roles in film and television.
  • B. Jerry Wisdom
    Jerry Wisdom was a Bahamian sprinter known for competing in international track and field events, including the Olympic Games.
  • C. Jack Wisdom
    Jack Wisdom is an American planetary scientist and MIT professor known for his work on celestial mechanics and dynamical chaos in the solar system.
  • D. Herbert Wise
    Herbert Wise was a British television and film director best known for his acclaimed work on period dramas and literary adaptations.
  • E. William Wise
    William Wise is an actor known for his role in the acclaimed drama film "In the Bedroom."
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d732c48c488190a2b3162202b74726 completed April 9, 2026, 5:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69de55fbfc70819098eb40cf0d1b9e8c completed April 14, 2026, 2:58 p.m.
NEDg Description generation batch_69de5eacae148190b7ca2da87427572e completed April 14, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_69de6397ff688190b6788489895a5360 completed April 14, 2026, 3:56 p.m.
Created at: April 8, 2026, 9:17 p.m.