Triple

T11166549
Position Surface form Disambiguated ID Type / Status
Subject Planet Her E264173 entity
Predicate producer P490 FINISHED
Object Kool Kojak
Kool Kojak is a Brazilian-American record producer and songwriter known for crafting pop and hip-hop hits for major artists across the 2010s and beyond.
 E908682 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: Kool Kojak | Statement: [Planet Her, producer, Kool Kojak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kool Kojak
Context triple: [Planet Her, producer, Kool Kojak]
  • A. Kojak
    Kojak is a 1970s American television crime drama series centered on the tough, lollipop-licking New York City detective Theo Kojak, played by Telly Savalas.
  • B. Chopmaster J
    Chopmaster J is an American hip hop producer and DJ best known as a founding member of the rap group Digital Underground.
  • C. Kenickie
    Kenickie is a tough, wisecracking member of the T-Birds gang and Danny Zuko’s best friend in the musical and film "Grease."
  • D. Kool
    Kool is a long-standing American menthol cigarette brand recognized for its distinctive marketing and association with menthol smoking.
  • E. American Koko
    American Koko is a satirical mystery web series that follows a quirky private investigator navigating race, identity, and social awkwardness in modern America.
  • 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: Kool Kojak
Triple: [Planet Her, producer, Kool Kojak]
Generated description
Kool Kojak is a Brazilian-American record producer and songwriter known for crafting pop and hip-hop hits for major artists across the 2010s and beyond.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kool Kojak
Target entity description: Kool Kojak is a Brazilian-American record producer and songwriter known for crafting pop and hip-hop hits for major artists across the 2010s and beyond.
  • A. Kojak
    Kojak is a 1970s American television crime drama series centered on the tough, lollipop-licking New York City detective Theo Kojak, played by Telly Savalas.
  • B. Chopmaster J
    Chopmaster J is an American hip hop producer and DJ best known as a founding member of the rap group Digital Underground.
  • C. Kenickie
    Kenickie is a tough, wisecracking member of the T-Birds gang and Danny Zuko’s best friend in the musical and film "Grease."
  • D. Kool
    Kool is a long-standing American menthol cigarette brand recognized for its distinctive marketing and association with menthol smoking.
  • E. American Koko
    American Koko is a satirical mystery web series that follows a quirky private investigator navigating race, identity, and social awkwardness in modern America.
  • 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e88843cc81909e503f0921c6d297 completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e463945e40819087c6bdbc322a6d54 completed April 19, 2026, 5:09 a.m.
NEDg Description generation batch_69e46c37efec81908aa709587c37569d completed April 19, 2026, 5:46 a.m.
NED2 Entity disambiguation (via description) batch_69e47292cdd08190b05c4c8b09f4f918 completed April 19, 2026, 6:13 a.m.
Created at: April 8, 2026, 9:29 p.m.