Triple

T8459534
Position Surface form Disambiguated ID Type / Status
Subject Bale Mountains National Park E200006 entity
Predicate nearestCity P350 FINISHED
Object Robe
Robe is a town in southeastern Ethiopia that serves as an important regional center and gateway to the nearby Bale Mountains.
 E735298 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: Robe | Statement: [Bale Mountains National Park, nearestCity, Robe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Robe
Context triple: [Bale Mountains National Park, nearestCity, Robe]
  • A. Robe
    Robe is a historic coastal town in South Australia known for its fishing industry, beaches, and heritage architecture.
  • B. Roby
    Roby is a suburban village and residential area within the Metropolitan Borough of Knowsley in Merseyside, England.
  • C. Rochon
    Rochon is a French-origin surname borne by various notable individuals in fields such as entertainment, science, and public service.
  • D. Robards
    Robards is a surname most prominently associated with the American stage and film actor Jason Robards.
  • E. Tailo
    Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
  • 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: Robe
Triple: [Bale Mountains National Park, nearestCity, Robe]
Generated description
Robe is a town in southeastern Ethiopia that serves as an important regional center and gateway to the nearby Bale Mountains.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Robe
Target entity description: Robe is a town in southeastern Ethiopia that serves as an important regional center and gateway to the nearby Bale Mountains.
  • A. Robe
    Robe is a historic coastal town in South Australia known for its fishing industry, beaches, and heritage architecture.
  • B. Roby
    Roby is a suburban village and residential area within the Metropolitan Borough of Knowsley in Merseyside, England.
  • C. Rochon
    Rochon is a French-origin surname borne by various notable individuals in fields such as entertainment, science, and public service.
  • D. Robards
    Robards is a surname most prominently associated with the American stage and film actor Jason Robards.
  • E. Tailo
    Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
  • 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_69ca83198c4c8190a337bf717d1813f5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe49e036c8190abb50ca272266ca6 completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1df214ac8190b59daa88e3a930bc completed April 2, 2026, 7:42 a.m.
NEDg Description generation batch_69ce21c53298819080137c87ff487b50 completed April 2, 2026, 7:59 a.m.
NED2 Entity disambiguation (via description) batch_69ce23d6da1c8190a28bc895d737595e completed April 2, 2026, 8:07 a.m.
Created at: March 30, 2026, 6:10 p.m.