Triple

T5018539
Position Surface form Disambiguated ID Type / Status
Subject Piper Kerman E112793 entity
Predicate familyName P18 FINISHED
Object Kerman
Kerman is the surname of Piper Kerman, the American author whose memoir inspired the television series "Orange Is the New Black."
 E486653 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: Kerman | Statement: [Piper Kerman, familyName, Kerman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kerman
Context triple: [Piper Kerman, familyName, Kerman]
  • A. Kerman
    Kerman is a small city in California’s San Joaquin Valley, known for its agricultural economy and location west of Fresno.
  • B. Kerman
    Kerman is a major city in southeastern Iran known for its rich history, traditional bazaars, and proximity to desert landscapes.
  • C. Birjand
    Birjand is a city in eastern Iran that serves as the capital of South Khorasan Province and is known for its historical forts and saffron production.
  • D. Yazd
    Yazd is an ancient desert city in central Iran known for its well-preserved mud-brick architecture, Zoroastrian heritage, and historically significant Jewish community.
  • E. Kermanshah
    Kermanshah is a major city in western Iran known for its rich Kurdish culture and proximity to important historical and archaeological sites.
  • 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: Kerman
Triple: [Piper Kerman, familyName, Kerman]
Generated description
Kerman is the surname of Piper Kerman, the American author whose memoir inspired the television series "Orange Is the New Black."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kerman
Target entity description: Kerman is the surname of Piper Kerman, the American author whose memoir inspired the television series "Orange Is the New Black."
  • A. Kerman
    Kerman is a small city in California’s San Joaquin Valley, known for its agricultural economy and location west of Fresno.
  • B. Kerman
    Kerman is a major city in southeastern Iran known for its rich history, traditional bazaars, and proximity to desert landscapes.
  • C. Birjand
    Birjand is a city in eastern Iran that serves as the capital of South Khorasan Province and is known for its historical forts and saffron production.
  • D. Yazd
    Yazd is an ancient desert city in central Iran known for its well-preserved mud-brick architecture, Zoroastrian heritage, and historically significant Jewish community.
  • E. Kermanshah
    Kermanshah is a major city in western Iran known for its rich Kurdish culture and proximity to important historical and archaeological sites.
  • 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_69bd4435c2f48190be593158cbfcf8a3 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73415e088190802f9bb283262386 completed March 20, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69be927bdfa481908a5face7b4fd7058 completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be93e00fc08190a0706dd7375020f5 completed March 21, 2026, 12:49 p.m.
NED2 Entity disambiguation (via description) batch_69be94a7e15481908f17feafb593b97b completed March 21, 2026, 12:52 p.m.
Created at: March 20, 2026, 1:35 p.m.