Triple

T10056496
Position Surface form Disambiguated ID Type / Status
Subject Roman Spain E208874 entity
Predicate majorCity P316 FINISHED
Object Clunia
Clunia was an important Roman city in Hispania known as a political and administrative center and for its extensive archaeological remains, including a large theater and forum.
 E838622 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: Clunia | Statement: [Roman Spain, majorCity, Clunia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Clunia
Context triple: [Roman Spain, majorCity, Clunia]
  • A. Clun
    Clun is a small historic village in the Shropshire Hills of England, known for its medieval castle ruins and picturesque rural setting.
  • B. Clunie
    Clunie is a small village in Perth and Kinross, Scotland, known for its historic parish church and scenic rural surroundings.
  • C. Drimnin
    Drimnin is a small coastal settlement on the Morvern peninsula in the Scottish Highlands, historically associated with the Clan Maclean.
  • D. Balclutha
    Balclutha is a historic 19th-century steel-hulled sailing ship preserved as a museum vessel in San Francisco.
  • E. Balclutha
    Balclutha is a small South Otago town in New Zealand, known as a key service and transport hub for the surrounding farming region.
  • 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: Clunia
Triple: [Roman Spain, majorCity, Clunia]
Generated description
Clunia was an important Roman city in Hispania known as a political and administrative center and for its extensive archaeological remains, including a large theater and forum.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Clunia
Target entity description: Clunia was an important Roman city in Hispania known as a political and administrative center and for its extensive archaeological remains, including a large theater and forum.
  • A. Clun
    Clun is a small historic village in the Shropshire Hills of England, known for its medieval castle ruins and picturesque rural setting.
  • B. Clunie
    Clunie is a small village in Perth and Kinross, Scotland, known for its historic parish church and scenic rural surroundings.
  • C. Drimnin
    Drimnin is a small coastal settlement on the Morvern peninsula in the Scottish Highlands, historically associated with the Clan Maclean.
  • D. Balclutha
    Balclutha is a historic 19th-century steel-hulled sailing ship preserved as a museum vessel in San Francisco.
  • E. Balclutha
    Balclutha is a small South Otago town in New Zealand, known as a key service and transport hub for the surrounding farming region.
  • 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_69ca836094408190a36a1ea7e9a86fcd completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcfae503881909b9f016da4e2207d completed April 2, 2026, 2:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29a5258788190a4ecdefa5b520609 completed April 5, 2026, 5:22 p.m.
NEDg Description generation batch_69d29b7430248190b8965eaf1286dd7c completed April 5, 2026, 5:27 p.m.
NED2 Entity disambiguation (via description) batch_69d29c7ba9f081908f4614098d6c954b completed April 5, 2026, 5:31 p.m.
Created at: March 30, 2026, 8:57 p.m.