Triple

T6117514
Position Surface form Disambiguated ID Type / Status
Subject Bob Bakish E136396 entity
Predicate familyName P18 FINISHED
Object Bakish
Bakish is the surname of Bob Bakish, an American media executive best known as the former president and CEO of Paramount Global (formerly ViacomCBS).
 E568924 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: Bakish | Statement: [Bob Bakish, familyName, Bakish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bakish
Context triple: [Bob Bakish, familyName, Bakish]
  • A. Baka
    Baka was an ancient Egyptian prince of the 4th Dynasty, likely a son of Pharaoh Djedefre and possibly associated with an unfinished pyramid at Zawyet El Aryan.
  • B. Bugaksan
    Bugaksan is a prominent mountain in central Seoul, South Korea, known for its historical city walls, scenic hiking trails, and views over the capital.
  • C. Bisharin
    Bisharin are a subgroup of the Beja people, traditionally semi-nomadic pastoralists inhabiting parts of northeastern Sudan and southern Egypt.
  • D. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • E. Bisher Bashi
    Bisher Bashi is a renowned Bengali poetry collection by Kazi Nazrul Islam, noted for its intense emotional expression and revolutionary themes.
  • 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: Bakish
Triple: [Bob Bakish, familyName, Bakish]
Generated description
Bakish is the surname of Bob Bakish, an American media executive best known as the former president and CEO of Paramount Global (formerly ViacomCBS).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bakish
Target entity description: Bakish is the surname of Bob Bakish, an American media executive best known as the former president and CEO of Paramount Global (formerly ViacomCBS).
  • A. Baka
    Baka was an ancient Egyptian prince of the 4th Dynasty, likely a son of Pharaoh Djedefre and possibly associated with an unfinished pyramid at Zawyet El Aryan.
  • B. Bugaksan
    Bugaksan is a prominent mountain in central Seoul, South Korea, known for its historical city walls, scenic hiking trails, and views over the capital.
  • C. Bisharin
    Bisharin are a subgroup of the Beja people, traditionally semi-nomadic pastoralists inhabiting parts of northeastern Sudan and southern Egypt.
  • D. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • E. Bisher Bashi
    Bisher Bashi is a renowned Bengali poetry collection by Kazi Nazrul Islam, noted for its intense emotional expression and revolutionary themes.
  • 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_69c05beb4cfc8190ab67a5338ec59cea completed March 22, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1256ddb38819095f582b6468db407 completed March 23, 2026, 11:35 a.m.
NEDg Description generation batch_69c125ede4f88190989a5a40accd2745 completed March 23, 2026, 11:37 a.m.
NED2 Entity disambiguation (via description) batch_69c1268ffc7481909a9bd2be039dbf45 completed March 23, 2026, 11:40 a.m.
Created at: March 22, 2026, 4:14 p.m.