Triple

T1600307
Position Surface form Disambiguated ID Type / Status
Subject Boston Braves (AHL) E34375 entity
Predicate notablePlayer P304 FINISHED
Object Doug Roberts
Doug Roberts is a former professional ice hockey player best known for his time in the NHL during the late 1960s and 1970s.
E180705 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: Doug Roberts | Statement: [Boston Braves (AHL), notablePlayer, Doug Roberts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doug Roberts
Context triple: [Boston Braves (AHL), notablePlayer, Doug Roberts]
  • A. Brian Turner
    Brian Turner is a notable activist recognized for his influential role in the Free Speech Movement.
  • B. William Faulks
    William Faulks is known as the son of British novelist Sebastian Faulks.
  • C. Jonathan Thomas
    Jonathan Thomas is best known as the longtime husband of acclaimed American playwright Edward Albee.
  • D. Jim Holland
    Jim Holland is the husband of Zimbabwean politician and human rights activist Sekai Holland.
  • E. Jack Higgins
    Jack Higgins was a bestselling British thriller novelist, best known for his World War II espionage novel "The Eagle Has Landed."
  • 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: Doug Roberts
Triple: [Boston Braves (AHL), notablePlayer, Doug Roberts]
Generated description
Doug Roberts is a former professional ice hockey player best known for his time in the NHL during the late 1960s and 1970s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doug Roberts
Target entity description: Doug Roberts is a former professional ice hockey player best known for his time in the NHL during the late 1960s and 1970s.
  • A. Brian Turner
    Brian Turner is a notable activist recognized for his influential role in the Free Speech Movement.
  • B. William Faulks
    William Faulks is known as the son of British novelist Sebastian Faulks.
  • C. Jonathan Thomas
    Jonathan Thomas is best known as the longtime husband of acclaimed American playwright Edward Albee.
  • D. Jack Higgins
    Jack Higgins was a bestselling British thriller novelist, best known for his World War II espionage novel "The Eagle Has Landed."
  • E. Andrew Bacevich
    Andrew Bacevich is an American historian, retired U.S. Army colonel, and prominent critic of U.S. foreign policy and militarism.
  • 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_69a885fdcb9c819081ce6f0b8cd477dd completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9094a27908190bf0d9b5d43617192 completed March 5, 2026, 4:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad46aafce08190855f8e0b760ab5ac completed March 8, 2026, 9:51 a.m.
NEDg Description generation batch_69ad47c7108081908e78a24983353212 completed March 8, 2026, 9:56 a.m.
NED2 Entity disambiguation (via description) batch_69ad481e2c788190af51003898fcbe33 completed March 8, 2026, 9:57 a.m.
Created at: March 4, 2026, 7:28 p.m.