Triple

T7283229
Position Surface form Disambiguated ID Type / Status
Subject Susa E163800 entity
Predicate hasLandmark P105 FINISHED
Object Susa Cathedral
Susa Cathedral is a historic Roman Catholic church and prominent religious landmark in the town of Susa in northern Italy.
E654965 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: Susa Cathedral | Statement: [Susa, hasLandmark, Susa Cathedral]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susa Cathedral
Context triple: [Susa, hasLandmark, Susa Cathedral]
  • A. Basilika
    Basilika is a comprehensive 9th-century Byzantine legal code that systematically revised and expanded Justinian’s laws into Greek.
  • B. Cathedral of Ani
    The Cathedral of Ani is a monumental medieval Armenian church renowned for its distinctive architecture and as a symbol of the former glory of the ancient city of Ani.
  • C. Susa Shrine
    Susa Shrine is a Shinto shrine in Japan dedicated to the storm god Susanoo, revered as one of the country’s ancient and significant religious sites.
  • D. Shira Cathedral
    Shira Cathedral is a prominent religious landmark and architectural centerpiece of the city of Shira.
  • E. Andria Cathedral
    Andria Cathedral is a historic Roman Catholic church in Andria, Italy, notable as the burial site of several medieval royals including Holy Roman Empress Isabella of England.
  • 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: Susa Cathedral
Triple: [Susa, hasLandmark, Susa Cathedral]
Generated description
Susa Cathedral is a historic Roman Catholic church and prominent religious landmark in the town of Susa in northern Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Susa Cathedral
Target entity description: Susa Cathedral is a historic Roman Catholic church and prominent religious landmark in the town of Susa in northern Italy.
  • A. Basilika
    Basilika is a comprehensive 9th-century Byzantine legal code that systematically revised and expanded Justinian’s laws into Greek.
  • B. Cathedral of Ani
    The Cathedral of Ani is a monumental medieval Armenian church renowned for its distinctive architecture and as a symbol of the former glory of the ancient city of Ani.
  • C. Susa Shrine
    Susa Shrine is a Shinto shrine in Japan dedicated to the storm god Susanoo, revered as one of the country’s ancient and significant religious sites.
  • D. Shira Cathedral
    Shira Cathedral is a prominent religious landmark and architectural centerpiece of the city of Shira.
  • E. Andria Cathedral
    Andria Cathedral is a historic Roman Catholic church in Andria, Italy, notable as the burial site of several medieval royals including Holy Roman Empress Isabella of England.
  • 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_69c6886093b88190a254b1ce6db8bae7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb4ec2088190a6713eaa221d49a6 completed March 27, 2026, 8:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7e5368794819084e50bc87d8264de completed March 28, 2026, 2:27 p.m.
NEDg Description generation batch_69c7e628b9e0819099fef480ea58973d completed March 28, 2026, 2:31 p.m.
NED2 Entity disambiguation (via description) batch_69c7e7582ab08190827bb04465297c7c completed March 28, 2026, 2:36 p.m.
Created at: March 27, 2026, 2:59 p.m.