Triple

T14063478
Position Surface form Disambiguated ID Type / Status
Subject Colony of Queensland E338401 entity
Predicate premier P307 FINISHED
Object Hugh Nelson
Hugh Nelson was a late 19th-century Australian politician who served as Premier of Queensland and later held senior roles in both state and federal politics.
E1081892 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: Hugh Nelson | Statement: [Colony of Queensland, premier, Hugh Nelson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Nelson
Context triple: [Colony of Queensland, premier, Hugh Nelson]
  • A. Hugh Nelson
    Hugh Nelson was a 19th-century Canadian politician and businessman who served as one of the first senators for British Columbia after Confederation.
  • B. Hugh Baird
    Hugh Baird was a Scottish civil engineer best known for his major role in early 19th-century canal design and construction.
  • C. Don Boyd
    Don Boyd is a British film producer and director known for his work on independent and socially conscious films.
  • D. John Houstoun
    John Houstoun was an American lawyer and politician who served as a governor of Georgia during the late 18th century.
  • E. Roy McGivern
    Roy McGivern is a Northern Irish football administrator best known for serving as chairman of Linfield FC, one of the country’s most successful and historic clubs.
  • 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: Hugh Nelson
Triple: [Colony of Queensland, premier, Hugh Nelson]
Generated description
Hugh Nelson was a late 19th-century Australian politician who served as Premier of Queensland and later held senior roles in both state and federal politics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hugh Nelson
Target entity description: Hugh Nelson was a late 19th-century Australian politician who served as Premier of Queensland and later held senior roles in both state and federal politics.
  • A. Hugh Nelson
    Hugh Nelson was a 19th-century Canadian politician and businessman who served as one of the first senators for British Columbia after Confederation.
  • B. Hugh Baird
    Hugh Baird was a Scottish civil engineer best known for his major role in early 19th-century canal design and construction.
  • C. Don Boyd
    Don Boyd is a British film producer and director known for his work on independent and socially conscious films.
  • D. John Houstoun
    John Houstoun was an American lawyer and politician who served as a governor of Georgia during the late 18th century.
  • E. Roy McGivern
    Roy McGivern is a Northern Irish football administrator best known for serving as chairman of Linfield FC, one of the country’s most successful and historic clubs.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5689c7f48190a47ca94eaa8a9ef9 completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdefcc5708190beacccaa978a4abd completed May 7, 2026, 6:50 p.m.
NEDg Description generation batch_69fcdfe73b488190b6642927627cdd1b completed May 7, 2026, 6:54 p.m.
NED2 Entity disambiguation (via description) batch_69fce0f77e108190a2712c51a7b56bfc completed May 7, 2026, 6:59 p.m.
Created at: April 9, 2026, 10:21 p.m.