Triple

T241678
Position Surface form Disambiguated ID Type / Status
Subject Uber E4943 entity
Predicate hasKeyPerson P256 FINISHED
Object Dara Khosrowshahi
Dara Khosrowshahi is an Iranian-American business executive best known as the CEO of Uber and former CEO of Expedia Group.
E33050 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: Dara Khosrowshahi | Statement: [Uber, hasKeyPerson, Dara Khosrowshahi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dara Khosrowshahi
Context triple: [Uber, hasKeyPerson, Dara Khosrowshahi]
  • A. Omid Kordestani
    Omid Kordestani is an Iranian-American business executive best known for senior leadership roles at major tech companies including Google and Twitter.
  • B. Amini
    Amini is a small inhabited coral island in India’s Lakshadweep archipelago, known for its coconut cultivation, coir products, and traditional craftsmanship.
  • C. Ramin
    Ramin is a masculine given name of Persian origin, commonly used in Iran and among Persian-speaking communities.
  • D. Mir Jafar
    Mir Jafar was an 18th-century Nawab of Bengal best known for his alliance with the British East India Company, which helped establish British colonial rule in India.
  • E. Hassan Aref
    Hassan Aref was a prominent physicist and engineer known for his pioneering contributions to fluid dynamics, particularly in vortex dynamics and chaotic advection.
  • 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: Dara Khosrowshahi
Triple: [Uber, hasKeyPerson, Dara Khosrowshahi]
Generated description
Dara Khosrowshahi is an Iranian-American business executive best known as the CEO of Uber and former CEO of Expedia Group.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dara Khosrowshahi
Target entity description: Dara Khosrowshahi is an Iranian-American business executive best known as the CEO of Uber and former CEO of Expedia Group.
  • A. Omid Kordestani
    Omid Kordestani is an Iranian-American business executive best known for senior leadership roles at major tech companies including Google and Twitter.
  • B. Amini
    Amini is a small inhabited coral island in India’s Lakshadweep archipelago, known for its coconut cultivation, coir products, and traditional craftsmanship.
  • C. Ramin
    Ramin is a masculine given name of Persian origin, commonly used in Iran and among Persian-speaking communities.
  • D. Mir Jafar
    Mir Jafar was an 18th-century Nawab of Bengal best known for his alliance with the British East India Company, which helped establish British colonial rule in India.
  • E. Hassan Aref
    Hassan Aref was a prominent physicist and engineer known for his pioneering contributions to fluid dynamics, particularly in vortex dynamics and chaotic advection.
  • 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_69a257c3d0708190b0871c4269d273e6 completed Feb. 28, 2026, 2:49 a.m.
NER Named-entity recognition batch_69a25cee6f208190b996be4faa700910 completed Feb. 28, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3765a652081909164489d1e3e39f6 completed Feb. 28, 2026, 11:12 p.m.
NEDg Description generation batch_69a37819afcc81909621442ca98a9baa completed Feb. 28, 2026, 11:19 p.m.
NED2 Entity disambiguation (via description) batch_69a378b9dc54819096a1d0899e8d8b92 completed Feb. 28, 2026, 11:22 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.