Triple

T4736765
Position Surface form Disambiguated ID Type / Status
Subject Marrakesh-Safi E105143 entity
Predicate contains P35 FINISHED
Object Safi
Safi is a historic Moroccan port city on the Atlantic coast known for its fishing industry, ceramics, and Portuguese-era fortifications.
 E467091 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: Safi | Statement: [Marrakesh-Safi, contains, Safi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Safi
Context triple: [Marrakesh-Safi, contains, Safi]
  • A. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • B. Shuafat
    Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
  • C. Nefza
    Nefza is a town in northwestern Tunisia known for its forests, lakes, and proximity to the Mediterranean coast within the Béja Governorate.
  • D. Skhirat
    Skhirat is a coastal town in western Morocco known for hosting key international political negotiations and agreements.
  • E. Salwa
    Salwa is a coastal residential district in Kuwait, located within the Hawalli Governorate and known for its mix of housing, schools, and local amenities.
  • 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: Safi
Triple: [Marrakesh-Safi, contains, Safi]
Generated description
Safi is a historic Moroccan port city on the Atlantic coast known for its fishing industry, ceramics, and Portuguese-era fortifications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Safi
Target entity description: Safi is a historic Moroccan port city on the Atlantic coast known for its fishing industry, ceramics, and Portuguese-era fortifications.
  • A. Safa
    Safa is a principal deity in the Uatsdin (Assian) neo-pagan religious tradition, revered within the reconstructed Ossetian pantheon.
  • B. Shuafat
    Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
  • C. Nefza
    Nefza is a town in northwestern Tunisia known for its forests, lakes, and proximity to the Mediterranean coast within the Béja Governorate.
  • D. Skhirat
    Skhirat is a coastal town in western Morocco known for hosting key international political negotiations and agreements.
  • E. Salwa
    Salwa is a coastal residential district in Kuwait, located within the Hawalli Governorate and known for its mix of housing, schools, and local amenities.
  • 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_69bd43ee52048190b81a4f066534ffb3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64831c58819098758ac1f7839b3a completed March 20, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a1796608190972865b2f6beef05 completed March 21, 2026, 6:26 a.m.
NEDg Description generation batch_69be3d2063e48190afb3fdfd5ad6749f completed March 21, 2026, 6:39 a.m.
NED2 Entity disambiguation (via description) batch_69be3d99a288819088e42e04de5c17a4 completed March 21, 2026, 6:41 a.m.
Created at: March 20, 2026, 1:19 p.m.