Triple

T14097011
Position Surface form Disambiguated ID Type / Status
Subject Cuenca E339278 entity
Predicate hasLandmark P105 FINISHED
Object Torre de Mangana
Torre de Mangana is a historic clock tower and emblematic monument overlooking the old town of Cuenca, Spain.
E1079886 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: Torre de Mangana | Statement: [Cuenca, hasLandmark, Torre de Mangana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torre de Mangana
Context triple: [Cuenca, hasLandmark, Torre de Mangana]
  • A. Torre de Menagem
    Torre de Menagem is a prominent medieval keep and defensive tower that dominates the historic skyline of Guarda in Portugal.
  • B. Torre de Bujaco
    Torre de Bujaco is a prominent medieval defensive tower in Cáceres, Spain, notable for its well-preserved architecture and role as an emblem of the city’s historic skyline.
  • C. Torre Mozza
    Torre Mozza is a historic tower and notable architectural landmark located in the Italian city of Rovigo.
  • D. Torre Aquila
    Torre Aquila is a historic medieval tower in Trento, Italy, renowned for its well-preserved Gothic frescoes depicting the Cycle of the Months.
  • E. Torre di Mola
    Torre di Mola is a historic coastal watchtower in Formia, Italy, built for defensive purposes and now recognized as one of the town’s notable medieval landmarks.
  • 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: Torre de Mangana
Triple: [Cuenca, hasLandmark, Torre de Mangana]
Generated description
Torre de Mangana is a historic clock tower and emblematic monument overlooking the old town of Cuenca, Spain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Torre de Mangana
Target entity description: Torre de Mangana is a historic clock tower and emblematic monument overlooking the old town of Cuenca, Spain.
  • A. Torre de Menagem
    Torre de Menagem is a prominent medieval keep and defensive tower that dominates the historic skyline of Guarda in Portugal.
  • B. Torre de Bujaco
    Torre de Bujaco is a prominent medieval defensive tower in Cáceres, Spain, notable for its well-preserved architecture and role as an emblem of the city’s historic skyline.
  • C. Torre Mozza
    Torre Mozza is a historic tower and notable architectural landmark located in the Italian city of Rovigo.
  • D. Torre Aquila
    Torre Aquila is a historic medieval tower in Trento, Italy, renowned for its well-preserved Gothic frescoes depicting the Cycle of the Months.
  • E. Torre di Mola
    Torre di Mola is a historic coastal watchtower in Formia, Italy, built for defensive purposes and now recognized as one of the town’s notable medieval landmarks.
  • 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_69d81c69b5c8819094aa1abf18302908 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5fb926288190a7f0f50d1d585d76 completed April 14, 2026, 3:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0adfc28819097a1bfd56739c286 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd41c84408190ab4bc885e7ba8f81 completed May 7, 2026, 6:04 p.m.
NED2 Entity disambiguation (via description) batch_69fcd4ab4b588190977b3dc2adc1f412 completed May 7, 2026, 6:06 p.m.
Created at: April 9, 2026, 10:22 p.m.