Triple

T6505100
Position Surface form Disambiguated ID Type / Status
Subject Southeast Sulawesi E149987 entity
Predicate hasCity P316 FINISHED
Object Raha
Raha is a coastal town and administrative center located on Muna Island in Southeast Sulawesi, Indonesia.
 E600648 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: Raha | Statement: [Southeast Sulawesi, hasCity, Raha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Raha
Context triple: [Southeast Sulawesi, hasCity, Raha]
  • A. Rahan
    Rahan is a rural village in County Offaly, Ireland, known for its historic religious and educational institutions and its proximity to the Grand Canal.
  • B. Rahanweyn
    Rahanweyn is a major dialect (often considered a distinct variety) of the Somali language spoken primarily by the Rahanweyn clan families in southern Somalia.
  • C. Orlandi Valuta
    Orlandi Valuta is a money transfer and financial services brand owned by Western Union, primarily serving customers in the United States and Latin America.
  • D. Khorumi
    Khorumi is a dynamic Georgian war dance characterized by powerful, martial movements and formations that depict battle scenes and military pride.
  • E. Gulden
    The Gulden was a historical European gold-based coin and monetary unit used in various German states, including Hesse-Kassel, before the adoption of more modern currencies.
  • 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: Raha
Triple: [Southeast Sulawesi, hasCity, Raha]
Generated description
Raha is a coastal town and administrative center located on Muna Island in Southeast Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Raha
Target entity description: Raha is a coastal town and administrative center located on Muna Island in Southeast Sulawesi, Indonesia.
  • A. Rahan
    Rahan is a rural village in County Offaly, Ireland, known for its historic religious and educational institutions and its proximity to the Grand Canal.
  • B. Rahanweyn
    Rahanweyn is a major dialect (often considered a distinct variety) of the Somali language spoken primarily by the Rahanweyn clan families in southern Somalia.
  • C. Orlandi Valuta
    Orlandi Valuta is a money transfer and financial services brand owned by Western Union, primarily serving customers in the United States and Latin America.
  • D. Khorumi
    Khorumi is a dynamic Georgian war dance characterized by powerful, martial movements and formations that depict battle scenes and military pride.
  • E. Gulden
    The Gulden was a historical European gold-based coin and monetary unit used in various German states, including Hesse-Kassel, before the adoption of more modern currencies.
  • 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_69c687ef291081909d437f035eef1cda completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c69966ff708190902c88cb6b48e5d7 completed March 27, 2026, 2:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb43db608190b785e77f6850bb6f completed March 27, 2026, 6:24 p.m.
NEDg Description generation batch_69c6cc96edd08190b0c0f1b49dd64160 completed March 27, 2026, 6:29 p.m.
NED2 Entity disambiguation (via description) batch_69c6cd8d15ec8190be5a8c5e3f201139 completed March 27, 2026, 6:33 p.m.
Created at: March 27, 2026, 1:43 p.m.