Triple

T11429730
Position Surface form Disambiguated ID Type / Status
Subject United States Marines under Robert E. Lee E270846 entity
Predicate notableMember P10 FINISHED
Object Israel Greene
Israel Greene was a U.S. Marine Corps officer best known for leading the Marines’ assault that captured abolitionist John Brown at Harpers Ferry in 1859.
E924918 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: Israel Greene | Statement: [United States Marines under Robert E. Lee, notableMember, Israel Greene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Israel Greene
Context triple: [United States Marines under Robert E. Lee, notableMember, Israel Greene]
  • A. Tamir Greenwood
    Tamir Greenwood is a child of Radiohead guitarist and composer Jonny Greenwood.
  • B. Martin Greenberg
    Martin Greenberg was an American publisher and editor best known for co-founding Gnome Press, which helped popularize early science fiction literature.
  • C. Daniel Green
    Daniel Green is a music producer known for his work on the track "Paradise."
  • D. Jeffrey Greenstein
    Jeffrey Greenstein is a film producer known for his work on action and genre movies, including the war drama "The Outpost."
  • E. Joshua Goldstein
    Joshua Goldstein is a political scientist best known for his influential work on international relations, war and peace studies, and global security.
  • 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: Israel Greene
Triple: [United States Marines under Robert E. Lee, notableMember, Israel Greene]
Generated description
Israel Greene was a U.S. Marine Corps officer best known for leading the Marines’ assault that captured abolitionist John Brown at Harpers Ferry in 1859.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Israel Greene
Target entity description: Israel Greene was a U.S. Marine Corps officer best known for leading the Marines’ assault that captured abolitionist John Brown at Harpers Ferry in 1859.
  • A. Tamir Greenwood
    Tamir Greenwood is a child of Radiohead guitarist and composer Jonny Greenwood.
  • B. Martin Greenberg
    Martin Greenberg was an American publisher and editor best known for co-founding Gnome Press, which helped popularize early science fiction literature.
  • C. Daniel Green
    Daniel Green is a music producer known for his work on the track "Paradise."
  • D. Jeffrey Greenstein
    Jeffrey Greenstein is a film producer known for his work on action and genre movies, including the war drama "The Outpost."
  • E. Joshua Goldstein
    Joshua Goldstein is a political scientist best known for his influential work on international relations, war and peace studies, and global security.
  • 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d806c1bfb881909720c74fe0fa837f completed April 9, 2026, 8:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8d923688190bb4d61d57768e10e completed April 20, 2026, 5:25 a.m.
NEDg Description generation batch_69e5c28e2dd481909b45a43b5825f393 completed April 20, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69e5c4722c348190a4c49edb1f6df240 completed April 20, 2026, 6:15 a.m.
Created at: April 8, 2026, 9:35 p.m.