Triple

T7591367
Position Surface form Disambiguated ID Type / Status
Subject Philadelphia Soul E179741 entity
Predicate formerHeadCoach P537 FINISHED
Object Doug Plank
Doug Plank is a former NFL safety for the Chicago Bears who later became a successful arena football coach.
E675335 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 Plank | Statement: [Philadelphia Soul, formerHeadCoach, Doug Plank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doug Plank
Context triple: [Philadelphia Soul, formerHeadCoach, Doug Plank]
  • A. Jon Plowman
    Jon Plowman is a British television producer best known for his influential work on BBC comedies, including series such as Absolutely Fabulous and The Office.
  • B. Sean Plaice
    Sean Plaice is an entrepreneur best known as a co-founder of the on-demand delivery service Postmates.
  • C. Matt Wolpert
    Matt Wolpert is a television writer and producer best known for co-creating the alternate-history space drama series "For All Mankind."
  • D. Dan Jinks
    Dan Jinks is an American film and television producer best known for acclaimed movies such as "American Beauty" and "Big Fish."
  • E. Gregg Palmer
    Gregg Palmer was an American character actor known for his rugged roles in Westerns and mid-20th-century 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: Doug Plank
Triple: [Philadelphia Soul, formerHeadCoach, Doug Plank]
Generated description
Doug Plank is a former NFL safety for the Chicago Bears who later became a successful arena football coach.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doug Plank
Target entity description: Doug Plank is a former NFL safety for the Chicago Bears who later became a successful arena football coach.
  • A. Jon Plowman
    Jon Plowman is a British television producer best known for his influential work on BBC comedies, including series such as Absolutely Fabulous and The Office.
  • B. Sean Plaice
    Sean Plaice is an entrepreneur best known as a co-founder of the on-demand delivery service Postmates.
  • C. Matt Wolpert
    Matt Wolpert is a television writer and producer best known for co-creating the alternate-history space drama series "For All Mankind."
  • D. Dan Jinks
    Dan Jinks is an American film and television producer best known for acclaimed movies such as "American Beauty" and "Big Fish."
  • E. Gregg Palmer
    Gregg Palmer was an American character actor known for his rugged roles in Westerns and mid-20th-century 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_69c69f335248819093c1006f30513708 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f9b746ac8190b255afdfb9635f72 completed March 27, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69c86192b5d88190b0a02cf303462bfb completed March 28, 2026, 11:17 p.m.
NEDg Description generation batch_69c8628d252c8190bc67e90f497f1ada completed March 28, 2026, 11:21 p.m.
NED2 Entity disambiguation (via description) batch_69c8631e5c2c8190b1c593ca9bbf039c completed March 28, 2026, 11:24 p.m.
Created at: March 27, 2026, 3:53 p.m.