Triple

T2219138
Position Surface form Disambiguated ID Type / Status
Subject Macmillan Publishers E48100 entity
Predicate foundedBy P104 FINISHED
Object Daniel Macmillan
Daniel Macmillan was a 19th-century British publisher and co-founder of the influential publishing house Macmillan Publishers.
 E257052 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: Daniel Macmillan | Statement: [Macmillan Publishers, foundedBy, Daniel Macmillan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Daniel Macmillan
Context triple: [Macmillan Publishers, foundedBy, Daniel Macmillan]
  • A. Ewen MacIntosh
    Ewen MacIntosh is a British actor and comedian best known for playing the deadpan accountant Keith Bishop in the original UK version of "The Office."
  • B. David Farquharson
    David Farquharson was an architect known for designing South Hall.
  • C. Douglas Hamilton
    Douglas Hamilton is a Scottish noble titleholder best known as the 8th Duke of Hamilton, a prominent aristocrat of the 18th century.
  • D. Duncan Stewart
    Duncan Stewart is a music producer best known for his work on U2’s album "Songs of Surrender."
  • E. Philip MacDonald
    Philip MacDonald was a British-born novelist and screenwriter best known for his crime and mystery fiction and his contributions to classic Hollywood films.
  • 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: Daniel Macmillan
Triple: [Macmillan Publishers, foundedBy, Daniel Macmillan]
Generated description
Daniel Macmillan was a 19th-century British publisher and co-founder of the influential publishing house Macmillan Publishers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Daniel Macmillan
Target entity description: Daniel Macmillan was a 19th-century British publisher and co-founder of the influential publishing house Macmillan Publishers.
  • A. Ewen MacIntosh
    Ewen MacIntosh is a British actor and comedian best known for playing the deadpan accountant Keith Bishop in the original UK version of "The Office."
  • B. David Farquharson
    David Farquharson was an architect known for designing South Hall.
  • C. Douglas Hamilton
    Douglas Hamilton is a Scottish noble titleholder best known as the 8th Duke of Hamilton, a prominent aristocrat of the 18th century.
  • D. Duncan Stewart
    Duncan Stewart is a music producer best known for his work on U2’s album "Songs of Surrender."
  • E. Philip MacDonald
    Philip MacDonald was a British-born novelist and screenwriter best known for his crime and mystery fiction and his contributions to classic Hollywood films.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc011d50c8190b1c375cc633f8189 completed March 7, 2026, 6:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae95fb20b88190b7e959b5d718fe73 completed March 9, 2026, 9:42 a.m.
NEDg Description generation batch_69ae96c5a6308190b970ec78984a4e8a completed March 9, 2026, 9:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae9728ebc081908e00e318bcd60e57 completed March 9, 2026, 9:47 a.m.
Created at: March 4, 2026, 7:46 p.m.