Triple

T17223024
Position Surface form Disambiguated ID Type / Status
Subject Mehdi Jomaa E418035 entity
Predicate familyName P18 FINISHED
Object Jomaa
Jomaa is a Tunisian surname most notably associated with Mehdi Jomaa, a former Prime Minister of Tunisia.
 E1257764 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: Jomaa | Statement: [Mehdi Jomaa, familyName, Jomaa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jomaa
Context triple: [Mehdi Jomaa, familyName, Jomaa]
  • A. Jakmèl
    Jakmèl is the Haitian Creole name for Jacmel, a historic coastal city in southern Haiti known for its vibrant arts scene, colonial architecture, and annual Carnival celebrations.
  • B. Jümme
    Jümme is a small river in Lower Saxony, Germany, known for flowing through the Leer district and contributing to the region’s network of waterways and wetlands.
  • C. Hajna
    Hajna is a feminine given name, notably borne by American actress and producer Hajna O. Moss.
  • D. Jogne
    Jogne is a river in western Switzerland that flows through the canton of Fribourg before joining the Sarine.
  • E. Jaru
    Jaru is a municipality in the Brazilian state of Rondônia, located in the northern region of the country within the Amazon basin.
  • 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: Jomaa
Triple: [Mehdi Jomaa, familyName, Jomaa]
Generated description
Jomaa is a Tunisian surname most notably associated with Mehdi Jomaa, a former Prime Minister of Tunisia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jomaa
Target entity description: Jomaa is a Tunisian surname most notably associated with Mehdi Jomaa, a former Prime Minister of Tunisia.
  • A. Jakmèl
    Jakmèl is the Haitian Creole name for Jacmel, a historic coastal city in southern Haiti known for its vibrant arts scene, colonial architecture, and annual Carnival celebrations.
  • B. Jümme
    Jümme is a small river in Lower Saxony, Germany, known for flowing through the Leer district and contributing to the region’s network of waterways and wetlands.
  • C. Hajna
    Hajna is a feminine given name, notably borne by American actress and producer Hajna O. Moss.
  • D. Jogne
    Jogne is a river in western Switzerland that flows through the canton of Fribourg before joining the Sarine.
  • E. Jaru
    Jaru is a municipality in the Brazilian state of Rondônia, located in the northern region of the country within the Amazon basin.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42ddf2c3c8190b6adceaaefd4ccbf completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0167596ab481909df59ce68c7f640e completed May 11, 2026, 5:21 a.m.
NEDg Description generation batch_6a0169f4d520819095774ce5ee2d2220 completed May 11, 2026, 5:32 a.m.
NED2 Entity disambiguation (via description) batch_6a016a55114881909496549dfb7b6ff1 completed May 11, 2026, 5:34 a.m.
Created at: April 10, 2026, 5:38 a.m.