Triple

T37284473
Position Surface form Disambiguated ID Type / Status
Subject Don Larsen's perfect game E925492 entity
Predicate firstBaseUmpire P205817 FINISHED
Object John Stevens
John Stevens was a Major League Baseball umpire best known for serving on the officiating crew during Don Larsen's perfect game in the 1956 World Series.
 E2226780 NE FINISHED

How this triple was built (3 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: John Stevens | Statement: [Don Larsen's perfect game, firstBaseUmpire, John Stevens]
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: John Stevens
Triple: [Don Larsen's perfect game, firstBaseUmpire, John Stevens]
Generated description
John Stevens was a Major League Baseball umpire best known for serving on the officiating crew during Don Larsen's perfect game in the 1956 World Series.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: firstBaseUmpire
Context triple: [Don Larsen's perfect game, firstBaseUmpire, John Stevens]
  • A. leftFieldUmpire
    Indicates that an entity serves as the umpire positioned in the left field area relative to a particular game or play.
  • B. thirdBaseUmpire
    Indicates that the subject serves as the umpire positioned at third base in a baseball game, responsible for making calls on plays occurring near that base.
  • C. secondBaseUmpire
    Indicates the relationship where an umpire is assigned to officiate plays at second base in a baseball game.
  • D. rightFieldUmpire
    Indicates that the subject is serving as the umpire positioned in right field in relation to the object (typically a game or play).
  • E. eraAsUmpire
    Indicates the time period during which an entity served in the role of an umpire.
  • F. None of above. chosen

Provenance (7 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_69f76eafe20c8190856d3b996a4c31a7 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a037cad051c8190b28b354b89208574 completed May 12, 2026, 7:17 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4082376c1881908385aac6145656da completed June 28, 2026, 2:08 a.m.
NEDg Description generation batch_6a408301ac7481909a67b2b663296357 completed June 28, 2026, 2:12 a.m.
NED2 Entity disambiguation (via description) batch_6a4083b93a508190819fe83da97374f7 completed June 28, 2026, 2:15 a.m.
PD Predicate disambiguation batch_6a037a11efc08190bb7cacc1325b4dc6 completed May 12, 2026, 7:05 p.m.
PDg Predicate description generation batch_6a037c842b2c819082f1d2db995ac2eb completed May 12, 2026, 7:16 p.m.
Created at: May 3, 2026, 4:16 p.m.