Triple

T13570746
Position Surface form Disambiguated ID Type / Status
Subject Saxon Shore forts E324152 entity
Predicate hasPart P35 FINISHED
Object Gariannonum
Gariannonum was a Roman coastal fort in eastern Britain that formed part of the late Roman Saxon Shore defensive system.
 E1049752 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: Gariannonum | Statement: [Saxon Shore forts, hasPart, Gariannonum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gariannonum
Context triple: [Saxon Shore forts, hasPart, Gariannonum]
  • A. Gesoriacum
    Gesoriacum was the ancient Roman name for the port city later known as Bononia (modern Boulogne-sur-Mer) in northern Gaul, an important maritime and military hub facing Britain.
  • B. Longiano
    Longiano is a historic hilltop town in Italy’s Emilia-Romagna region, known for its medieval castle, scenic views, and well-preserved old center.
  • C. Andecavorum
    Andecavorum is the ancient Latin name for the city now known as Angers in western France.
  • D. Gortys
    Gortys is a cheerful, childlike robot from the episodic game Tales from the Borderlands, central to the story’s search for a fabled Vault.
  • E. Arycanda
    Arycanda was an ancient Lycian city in what is now southwestern Turkey, noted for its well-preserved ruins and terraced layout on a steep mountainside.
  • 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: Gariannonum
Triple: [Saxon Shore forts, hasPart, Gariannonum]
Generated description
Gariannonum was a Roman coastal fort in eastern Britain that formed part of the late Roman Saxon Shore defensive system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gariannonum
Target entity description: Gariannonum was a Roman coastal fort in eastern Britain that formed part of the late Roman Saxon Shore defensive system.
  • A. Gesoriacum
    Gesoriacum was the ancient Roman name for the port city later known as Bononia (modern Boulogne-sur-Mer) in northern Gaul, an important maritime and military hub facing Britain.
  • B. Longiano
    Longiano is a historic hilltop town in Italy’s Emilia-Romagna region, known for its medieval castle, scenic views, and well-preserved old center.
  • C. Andecavorum
    Andecavorum is the ancient Latin name for the city now known as Angers in western France.
  • D. Gortys
    Gortys is a cheerful, childlike robot from the episodic game Tales from the Borderlands, central to the story’s search for a fabled Vault.
  • E. Arycanda
    Arycanda was an ancient Lycian city in what is now southwestern Turkey, noted for its well-preserved ruins and terraced layout on a steep mountainside.
  • 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_69d8076830b48190910a902bae5888e2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb00f5b8881908617f42d227ed137 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bb61a40819099a62f65a68dff7b completed May 3, 2026, 3:37 p.m.
NEDg Description generation batch_69f77640b5308190aaa50e8d5d871832 completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f779178dc48190bb0de790de30d8b0 completed May 3, 2026, 4:34 p.m.
Created at: April 9, 2026, 9:48 p.m.