Triple

T3195194
Position Surface form Disambiguated ID Type / Status
Subject Hydra E66917 entity
Predicate hasSettlement P1068 FINISHED
Object Mandraki
Mandraki is the main port town and one of the primary settlements on the Greek island of Hydra, known for its traditional architecture and seaside setting.
 E335944 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: Mandraki | Statement: [Hydra, hasSettlement, Mandraki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mandraki
Context triple: [Hydra, hasSettlement, Mandraki]
  • A. Mnajdra
    Mnajdra is an ancient megalithic temple complex on Malta’s southern coast, renowned for its prehistoric architecture and astronomical alignments.
  • B. Velia
    Velia was an important ancient Greek coastal city in Lucania, southern Italy, known for its role as a philosophical center of the Eleatic school.
  • C. Malax
    Malax is a small coastal municipality in western Finland known for its Swedish-speaking majority and rural Ostrobothnian landscapes.
  • D. Mola
    Mola is a Spanish surname most notably associated with Emilio Mola, a key Nationalist general during the Spanish Civil War.
  • E. Diadema
    Diadema is an industrial and densely populated municipality in the Greater São Paulo metropolitan area of southeastern Brazil.
  • 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: Mandraki
Triple: [Hydra, hasSettlement, Mandraki]
Generated description
Mandraki is the main port town and one of the primary settlements on the Greek island of Hydra, known for its traditional architecture and seaside setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mandraki
Target entity description: Mandraki is the main port town and one of the primary settlements on the Greek island of Hydra, known for its traditional architecture and seaside setting.
  • A. Mnajdra
    Mnajdra is an ancient megalithic temple complex on Malta’s southern coast, renowned for its prehistoric architecture and astronomical alignments.
  • B. Velia
    Velia was an important ancient Greek coastal city in Lucania, southern Italy, known for its role as a philosophical center of the Eleatic school.
  • C. Malax
    Malax is a small coastal municipality in western Finland known for its Swedish-speaking majority and rural Ostrobothnian landscapes.
  • D. Mola
    Mola is a Spanish surname most notably associated with Emilio Mola, a key Nationalist general during the Spanish Civil War.
  • E. Diadema
    Diadema is an industrial and densely populated municipality in the Greater São Paulo metropolitan area of southeastern Brazil.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7163c6c8190b26b05b66740264d completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24bb2c9908190b3abc395537e22ac completed March 12, 2026, 5:14 a.m.
NEDg Description generation batch_69b24cda28308190b33f189b8c7f3c58 completed March 12, 2026, 5:19 a.m.
NED2 Entity disambiguation (via description) batch_69b24d84f29c819087c15fd3883d6657 completed March 12, 2026, 5:22 a.m.
Created at: March 8, 2026, 3:07 p.m.