Triple

T656442
Position Surface form Disambiguated ID Type / Status
Subject Hijazi Arabic E11659 entity
Predicate spokenIn P2266 FINISHED
Object Yanbu
Yanbu is a coastal city in western Saudi Arabia on the Red Sea, known as an industrial and port hub in the Medina Province.
 E91777 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: Yanbu | Statement: [Hijazi Arabic, spokenIn, Yanbu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yanbu
Context triple: [Hijazi Arabic, spokenIn, Yanbu]
  • A. Diriyah
    Diriyah is a historic town in Saudi Arabia that served as the original home of the Saudi royal family and the capital of the first Saudi state.
  • B. Kel Ajjer
    Kel Ajjer is a prominent Tuareg confederation traditionally inhabiting the central Sahara region spanning parts of present-day Algeria and Libya.
  • C. al-Wasta
    al-Wasta is a town in Egypt’s Beni Suef Governorate, located in Upper Egypt along the Nile River.
  • D. Badr City
    Badr City is a planned satellite city in Egypt that forms part of the Greater Cairo metropolitan area, known for its industrial zones and residential developments.
  • E. Zarqa
    Zarqa is a large industrial city in northeastern Jordan known for its factories, military presence, and role as a key economic hub.
  • 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: Yanbu
Triple: [Hijazi Arabic, spokenIn, Yanbu]
Generated description
Yanbu is a coastal city in western Saudi Arabia on the Red Sea, known as an industrial and port hub in the Medina Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yanbu
Target entity description: Yanbu is a coastal city in western Saudi Arabia on the Red Sea, known as an industrial and port hub in the Medina Province.
  • A. Diriyah
    Diriyah is a historic town in Saudi Arabia that served as the original home of the Saudi royal family and the capital of the first Saudi state.
  • B. Kel Ajjer
    Kel Ajjer is a prominent Tuareg confederation traditionally inhabiting the central Sahara region spanning parts of present-day Algeria and Libya.
  • C. al-Wasta
    al-Wasta is a town in Egypt’s Beni Suef Governorate, located in Upper Egypt along the Nile River.
  • D. Badr City
    Badr City is a planned satellite city in Egypt that forms part of the Greater Cairo metropolitan area, known for its industrial zones and residential developments.
  • E. Zarqa
    Zarqa is a large industrial city in northeastern Jordan known for its factories, military presence, and role as a key economic hub.
  • 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_69a4932862a0819098be659c814e4981 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49f4e87408190b5276d2b913d0426 completed March 1, 2026, 8:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69a66d8cd1e481908b77e4db0b6681bf completed March 3, 2026, 5:11 a.m.
NEDg Description generation batch_69a66e16c7bc8190a6aea054bac99c4c completed March 3, 2026, 5:13 a.m.
NED2 Entity disambiguation (via description) batch_69a66e7dd53c8190bdb3768abd80ba8d completed March 3, 2026, 5:15 a.m.
Created at: March 1, 2026, 7:36 p.m.