Triple

T12014102
Position Surface form Disambiguated ID Type / Status
Subject James Longstreet E285978 entity
Predicate alsoKnownAs P39 FINISHED
Object Pete
Pete is the nickname of James Longstreet, a prominent Confederate general during the American Civil War.
E285978 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: Pete | Statement: [James Longstreet, alsoKnownAs, Pete]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pete
Context triple: [James Longstreet, alsoKnownAs, Pete]
  • A. Pete
    Pete is the nickname of Grover Cleveland Alexander, a Hall of Fame Major League Baseball pitcher and one of the greatest hurlers of the early 20th century.
  • B. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • C. Pete
    Pete is a classic Disney cartoon villain, best known as Mickey Mouse’s burly, antagonistic foe in the Mickey Mouse franchise.
  • D. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • E. Pete
    Pete is the young orphaned boy who befriends and is protected by a friendly dragon in the Disney film "Pete's Dragon."
  • 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: Pete
Triple: [James Longstreet, alsoKnownAs, Pete]
Generated description
Pete is the nickname of James Longstreet, a prominent Confederate general during the American Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pete
Target entity description: Pete is the nickname of James Longstreet, a prominent Confederate general during the American Civil War.
  • A. Pete chosen
    Pete is the well-known nickname of Confederate General James Longstreet, one of Robert E. Lee’s principal corps commanders during the American Civil War.
  • B. Pete
    Pete is the nickname of Grover Cleveland Alexander, a Hall of Fame Major League Baseball pitcher and one of the greatest hurlers of the early 20th century.
  • C. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • D. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • E. Pete
    Pete is the nickname of American test pilot and astronaut William "Pete" Knight, known for setting a world speed record in the X-15 rocket plane.
  • F. None of above.

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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903d884488190b4450a98088208ef completed April 10, 2026, 2:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49d4156ec8190bfc6d1180ac41d06 completed May 1, 2026, 12:32 p.m.
NEDg Description generation batch_69f53d8ec5448190b303624887f7fa05 completed May 1, 2026, 11:56 p.m.
NED2 Entity disambiguation (via description) batch_69f564d2b4348190abf2d09ae00aea37 completed May 2, 2026, 2:43 a.m.
Created at: April 8, 2026, 9:46 p.m.