Triple

T20318971
Position Surface form Disambiguated ID Type / Status
Subject Dan Mullen E492155 entity
Predicate hasChild P369 FINISHED
Object Canon Mullen
Canon Mullen is one of the children of American college football coach Dan Mullen.
E1432613 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: Canon Mullen | Statement: [Dan Mullen, hasChild, Canon Mullen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canon Mullen
Context triple: [Dan Mullen, hasChild, Canon Mullen]
  • A. Roger Mullin
    Roger Mullin is a Scottish politician and academic who served as the Scottish National Party Member of Parliament for Kirkcaldy and Cowdenbeath.
  • B. Jerry Murrell
    Jerry Murrell is an American entrepreneur best known for creating and expanding the Five Guys burger restaurant chain into a major fast-casual brand.
  • C. John Milledge
    John Milledge was an American politician and statesman who served as governor of Georgia and a U.S. congressman in the early 19th century.
  • D. William Mullins
    William Mullins was an early 17th-century English colonist and Mayflower passenger, known as the father of fellow passenger Priscilla Mullins.
  • E. John McCausland
    John McCausland was a Confederate brigadier general in the American Civil War, noted for his cavalry leadership and controversial burning of Chambersburg, Pennsylvania.
  • 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: Canon Mullen
Triple: [Dan Mullen, hasChild, Canon Mullen]
Generated description
Canon Mullen is one of the children of American college football coach Dan Mullen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Canon Mullen
Target entity description: Canon Mullen is one of the children of American college football coach Dan Mullen.
  • A. Roger Mullin
    Roger Mullin is a Scottish politician and academic who served as the Scottish National Party Member of Parliament for Kirkcaldy and Cowdenbeath.
  • B. Jerry Murrell
    Jerry Murrell is an American entrepreneur best known for creating and expanding the Five Guys burger restaurant chain into a major fast-casual brand.
  • C. John Milledge
    John Milledge was an American politician and statesman who served as governor of Georgia and a U.S. congressman in the early 19th century.
  • D. William Mullins
    William Mullins was an early 17th-century English colonist and Mayflower passenger, known as the father of fellow passenger Priscilla Mullins.
  • E. John McCausland
    John McCausland was a Confederate brigadier general in the American Civil War, noted for his cavalry leadership and controversial burning of Chambersburg, Pennsylvania.
  • 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_69e0b4a0134081909113563e1c3ba68a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67789d8108190ae2e134f4b0b0be5 completed April 20, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a088afcd0c881908dfe3294d4620a54 completed May 16, 2026, 3:19 p.m.
NEDg Description generation batch_6a088c2bb7c48190b5d6d6d4cddce2c5 completed May 16, 2026, 3:24 p.m.
NED2 Entity disambiguation (via description) batch_6a088c8e936c8190897293a0edcdfef9 completed May 16, 2026, 3:26 p.m.
Created at: April 16, 2026, 11:20 a.m.