Triple

T1162603
Position Surface form Disambiguated ID Type / Status
Subject Marrakesh E24526 entity
Predicate nickname P55 FINISHED
Object Ochre City
Ochre City is a popular nickname for Marrakesh, referring to the Moroccan city's distinctive red and ochre-colored buildings and walls.
E137064 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: Ochre City | Statement: [Marrakesh, nickname, Ochre City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ochre City
Context triple: [Marrakesh, nickname, Ochre City]
  • A. Camel City
    Camel City is a nickname for Winston-Salem, North Carolina, historically tied to the city’s association with the Camel cigarette brand and its tobacco industry.
  • B. Crown City
    Crown City is a nickname for Pasadena, California, highlighting its reputation as an elegant, historically rich city known for events like the Rose Parade.
  • C. Golden City
    Golden City is a poetic nickname for Prague, highlighting the city's historic skyline of gilded spires and sunlit architecture.
  • D. Limestone City
    Limestone City is a nickname for Kingston, Ontario, reflecting its many historic buildings constructed from local limestone.
  • E. River City
    River City is a popular nickname for Sacramento, California, highlighting the city’s close connection to the nearby American and Sacramento Rivers.
  • 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: Ochre City
Triple: [Marrakesh, nickname, Ochre City]
Generated description
Ochre City is a popular nickname for Marrakesh, referring to the Moroccan city's distinctive red and ochre-colored buildings and walls.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ochre City
Target entity description: Ochre City is a popular nickname for Marrakesh, referring to the Moroccan city's distinctive red and ochre-colored buildings and walls.
  • A. Camel City
    Camel City is a nickname for Winston-Salem, North Carolina, historically tied to the city’s association with the Camel cigarette brand and its tobacco industry.
  • B. Crown City
    Crown City is a nickname for Pasadena, California, highlighting its reputation as an elegant, historically rich city known for events like the Rose Parade.
  • C. Golden City
    Golden City is a poetic nickname for Prague, highlighting the city's historic skyline of gilded spires and sunlit architecture.
  • D. Limestone City
    Limestone City is a nickname for Kingston, Ontario, reflecting its many historic buildings constructed from local limestone.
  • E. River City
    River City is a popular nickname for Sacramento, California, highlighting the city’s close connection to the nearby American and Sacramento Rivers.
  • 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_69a494060e148190abb42f971242c197 completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bcb2bb84819088bd94e91c10fb0c completed March 1, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7642ff0c81909b323ac328b18e2e completed March 7, 2026, 7:02 p.m.
NEDg Description generation batch_69ac76f20f308190be3c831eb2d59763 completed March 7, 2026, 7:05 p.m.
NED2 Entity disambiguation (via description) batch_69ac77585c708190b5f4b239d9574cd7 completed March 7, 2026, 7:07 p.m.
Created at: March 1, 2026, 7:45 p.m.