Triple

T6049978
Position Surface form Disambiguated ID Type / Status
Subject Hornets E134765 entity
Predicate athleticDirector P745 FINISHED
Object Mark Orr
Mark Orr is a collegiate sports administrator who serves as the athletic director for the Sacramento State Hornets.
E575953 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: Mark Orr | Statement: [Hornets, athleticDirector, Mark Orr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Orr
Context triple: [Hornets, athleticDirector, Mark Orr]
  • A. Eric Orsborn
    Eric Orsborn is an American local government leader serving as the mayor of Buckeye, Arizona.
  • B. Tim Orr
    Tim Orr is an American cinematographer known for his frequent collaborations with director David Gordon Green on independent and studio films.
  • C. Mark Okerstrom
    Mark Okerstrom is a Canadian business executive best known for serving as the former CEO of Expedia Group.
  • D. Michael Wells
    Michael Wells is a musician best known as a member of the American alternative country/rock band The Walkabouts.
  • E. Guy Oliver
    Guy Oliver was an American character actor of the silent film era who appeared in numerous early 20th-century motion pictures.
  • 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: Mark Orr
Triple: [Hornets, athleticDirector, Mark Orr]
Generated description
Mark Orr is a collegiate sports administrator who serves as the athletic director for the Sacramento State Hornets.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mark Orr
Target entity description: Mark Orr is a collegiate sports administrator who serves as the athletic director for the Sacramento State Hornets.
  • A. Eric Orsborn
    Eric Orsborn is an American local government leader serving as the mayor of Buckeye, Arizona.
  • B. Tim Orr
    Tim Orr is an American cinematographer known for his frequent collaborations with director David Gordon Green on independent and studio films.
  • C. Mark Okerstrom
    Mark Okerstrom is a Canadian business executive best known for serving as the former CEO of Expedia Group.
  • D. Michael Wells
    Michael Wells is a musician best known as a member of the American alternative country/rock band The Walkabouts.
  • E. Guy Oliver
    Guy Oliver was an American character actor of the silent film era who appeared in numerous early 20th-century motion pictures.
  • 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_69c00876a69881908088a2626d3b2666 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056f4f84c8190a7e2416d81b3554c completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16ea1595c8190926a5ed8d230ab4a completed March 23, 2026, 4:47 p.m.
NEDg Description generation batch_69c1c533f43881908d57b75237f3c827 completed March 23, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_69c1c59ef9b0819091b05cd30c07d918 completed March 23, 2026, 10:58 p.m.
Created at: March 22, 2026, 4:09 p.m.