Triple

T6124260
Position Surface form Disambiguated ID Type / Status
Subject Seymour Hersh E136556 entity
Predicate familyName P18 FINISHED
Object Hersh
Hersh is the surname of Seymour Hersh, a prominent American investigative journalist known for exposing major political and military scandals.
 E570501 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: Hersh | Statement: [Seymour Hersh, familyName, Hersh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hersh
Context triple: [Seymour Hersh, familyName, Hersh]
  • A. Hellman
    Hellman is a surname most notably associated with Martin Hellman, the American cryptologist and co-inventor of the Diffie–Hellman key exchange.
  • B. Heller
    Heller is a surname shared by various notable individuals across fields such as film, literature, science, and politics.
  • C. Heller
    The Heller is a river in Germany that serves as a right-bank tributary of the Sieg.
  • D. Hoffer
    Hoffer is a surname most notably associated with Abram Hoffer, a Canadian psychiatrist known for his work in orthomolecular medicine and niacin therapy for mental illness.
  • E. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • 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: Hersh
Triple: [Seymour Hersh, familyName, Hersh]
Generated description
Hersh is the surname of Seymour Hersh, a prominent American investigative journalist known for exposing major political and military scandals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hersh
Target entity description: Hersh is the surname of Seymour Hersh, a prominent American investigative journalist known for exposing major political and military scandals.
  • A. Hellman
    Hellman is a surname most notably associated with Martin Hellman, the American cryptologist and co-inventor of the Diffie–Hellman key exchange.
  • B. Heller
    Heller is a surname shared by various notable individuals across fields such as film, literature, science, and politics.
  • C. Heller
    The Heller is a river in Germany that serves as a right-bank tributary of the Sieg.
  • D. Hoffer
    Hoffer is a surname most notably associated with Abram Hoffer, a Canadian psychiatrist known for his work in orthomolecular medicine and niacin therapy for mental illness.
  • E. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • 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_69c0089f851c81909e5e189a617dcff6 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05c25976081909e0a40e07dff0b8a completed March 22, 2026, 9:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135b2500c8190aaf67b059ccbe3f1 completed March 23, 2026, 12:44 p.m.
NEDg Description generation batch_69c13769a4bc81908d45d371e77f8d32 completed March 23, 2026, 12:51 p.m.
NED2 Entity disambiguation (via description) batch_69c138247e2c8190b6c2aabbd36ad9c0 completed March 23, 2026, 12:55 p.m.
Created at: March 22, 2026, 4:14 p.m.