Triple

T4112618
Position Surface form Disambiguated ID Type / Status
Subject Moncef Marzouki E90210 entity
Predicate headOfGovernment P307 FINISHED
Object Mehdi Jomaa
Mehdi Jomaa is a Tunisian engineer and politician who served as Tunisia’s interim prime minister during the country’s post-revolution transitional period.
E418035 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: Mehdi Jomaa | Statement: [Moncef Marzouki, headOfGovernment, Mehdi Jomaa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mehdi Jomaa
Context triple: [Moncef Marzouki, headOfGovernment, Mehdi Jomaa]
  • A. Ahmed Hachani
    Ahmed Hachani is a Tunisian politician who has served as head of government under President Kais Saied.
  • B. Omar Ben Hassen
    Omar Ben Hassen is an American poet and spoken-word artist best known as a key member of the politically charged, pioneering hip-hop precursor group The Last Poets.
  • C. Hamadi Jebali
    Hamadi Jebali is a Tunisian politician and former prime minister who played a key role in the country’s post-Arab Spring transitional government.
  • D. Mohamed Ridouani
    Mohamed Ridouani is a Belgian politician who serves as the mayor of the city of Leuven.
  • E. Ali Laarayedh
    Ali Laarayedh is a Tunisian politician and former prime minister who played a key role in the country’s post-Arab Spring transitional government.
  • 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: Mehdi Jomaa
Triple: [Moncef Marzouki, headOfGovernment, Mehdi Jomaa]
Generated description
Mehdi Jomaa is a Tunisian engineer and politician who served as Tunisia’s interim prime minister during the country’s post-revolution transitional period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mehdi Jomaa
Target entity description: Mehdi Jomaa is a Tunisian engineer and politician who served as Tunisia’s interim prime minister during the country’s post-revolution transitional period.
  • A. Ahmed Hachani
    Ahmed Hachani is a Tunisian politician who has served as head of government under President Kais Saied.
  • B. Omar Ben Hassen
    Omar Ben Hassen is an American poet and spoken-word artist best known as a key member of the politically charged, pioneering hip-hop precursor group The Last Poets.
  • C. Hamadi Jebali
    Hamadi Jebali is a Tunisian politician and former prime minister who played a key role in the country’s post-Arab Spring transitional government.
  • D. Mohamed Ridouani
    Mohamed Ridouani is a Belgian politician who serves as the mayor of the city of Leuven.
  • E. Ali Laarayedh
    Ali Laarayedh is a Tunisian politician and former prime minister who played a key role in the country’s post-Arab Spring transitional government.
  • 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_69aed95c080881908125e30c5dcdc6f8 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af01decd808190b4e5a5f76b090b0a completed March 9, 2026, 5:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f1f8ca0819090fb2acb3fe03d14 completed March 14, 2026, 3:30 p.m.
NEDg Description generation batch_69b582f9c858819094de05e240c98594 completed March 14, 2026, 3:47 p.m.
NED2 Entity disambiguation (via description) batch_69b5836543848190abbf31c04804358d completed March 14, 2026, 3:48 p.m.
Created at: March 9, 2026, 3:41 p.m.