Triple

T22208761
Position Surface form Disambiguated ID Type / Status
Subject Spike Feresten E548885 entity
Predicate familyName P18 FINISHED
Object Feresten
Feresten is the surname of Spike Feresten, an American television writer, comedian, and talk show host known for his work on shows like Seinfeld and Late Show with David Letterman.
 E1524454 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: Feresten | Statement: [Spike Feresten, familyName, Feresten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Feresten
Context triple: [Spike Feresten, familyName, Feresten]
  • A. Zefta
    Zefta is a village located in southern Lebanon within the Nabatieh Governorate.
  • B. Bazarduzu
    Bazarduzu is the highest mountain in Azerbaijan, located in the Greater Caucasus range on the border with Russia.
  • C. Lapseki
    Lapseki is a town and district in Çanakkale Province in northwestern Turkey, situated on the Asian shore of the Dardanelles Strait.
  • D. Zangilan
    Zangilan is a town in southwestern Azerbaijan that serves as an administrative and transport hub near the borders with Armenia and Iran.
  • E. Fering
    Fering is a North Frisian dialect spoken primarily on the island of Föhr in Germany.
  • 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: Feresten
Triple: [Spike Feresten, familyName, Feresten]
Generated description
Feresten is the surname of Spike Feresten, an American television writer, comedian, and talk show host known for his work on shows like Seinfeld and Late Show with David Letterman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Feresten
Target entity description: Feresten is the surname of Spike Feresten, an American television writer, comedian, and talk show host known for his work on shows like Seinfeld and Late Show with David Letterman.
  • A. Zefta
    Zefta is a village located in southern Lebanon within the Nabatieh Governorate.
  • B. Bazarduzu
    Bazarduzu is the highest mountain in Azerbaijan, located in the Greater Caucasus range on the border with Russia.
  • C. Lapseki
    Lapseki is a town and district in Çanakkale Province in northwestern Turkey, situated on the Asian shore of the Dardanelles Strait.
  • D. Zangilan
    Zangilan is a town in southwestern Azerbaijan that serves as an administrative and transport hub near the borders with Armenia and Iran.
  • E. Fering
    Fering is a North Frisian dialect spoken primarily on the island of Föhr in Germany.
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b29eb808190ab8abaa1e0e354fa completed April 28, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0aa61b30248190b5097435ade9aea0 completed May 18, 2026, 5:39 a.m.
NEDg Description generation batch_6a0aa6d1f634819082d1edd70217b70c completed May 18, 2026, 5:42 a.m.
NED2 Entity disambiguation (via description) batch_6a0aa7879e048190bd4b8e7f7cfbaec4 completed May 18, 2026, 5:45 a.m.
Created at: April 16, 2026, 8:36 p.m.