Triple

T10475569
Position Surface form Disambiguated ID Type / Status
Subject Legio VII Gemina E247037 entity
Predicate hasCognomen P6662 FINISHED
Object Gemina
Gemina is the cognomen of the Roman imperial legion Legio VII Gemina, a military unit stationed primarily in Hispania during the early Empire.
 E865714 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: Gemina | Statement: [Legio VII Gemina, hasCognomen, Gemina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gemina
Context triple: [Legio VII Gemina, hasCognomen, Gemina]
  • A. Leonae
    Leonae is a variant form of the given name Leona, typically used as a feminine personal name.
  • B. Adrestia
    Adrestia is a lesser-known Greek goddess associated with revolt, retribution, and the balance between war and peace.
  • C. Vicetia
    Vicetia, known today as Vicenza, is an historic city in northeastern Italy that was a significant center of the ancient Veneti people and is now renowned for its Palladian architecture and UNESCO World Heritage status.
  • D. Hilaeira
    Hilaeira is a figure in Greek mythology, one of the daughters of Leucippus who, along with her sister Phoebe, was abducted by the Dioscuri, Castor and Pollux.
  • E. Gemini
    Gemini is a Tamil-language action film starring Vikram, known for its blend of crime drama and commercial entertainment.
  • 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: Gemina
Triple: [Legio VII Gemina, hasCognomen, Gemina]
Generated description
Gemina is the cognomen of the Roman imperial legion Legio VII Gemina, a military unit stationed primarily in Hispania during the early Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gemina
Target entity description: Gemina is the cognomen of the Roman imperial legion Legio VII Gemina, a military unit stationed primarily in Hispania during the early Empire.
  • A. Leonae
    Leonae is a variant form of the given name Leona, typically used as a feminine personal name.
  • B. Adrestia
    Adrestia is a lesser-known Greek goddess associated with revolt, retribution, and the balance between war and peace.
  • C. Vicetia
    Vicetia, known today as Vicenza, is an historic city in northeastern Italy that was a significant center of the ancient Veneti people and is now renowned for its Palladian architecture and UNESCO World Heritage status.
  • D. Hilaeira
    Hilaeira is a figure in Greek mythology, one of the daughters of Leucippus who, along with her sister Phoebe, was abducted by the Dioscuri, Castor and Pollux.
  • E. Gemini
    Gemini is a Tamil-language action film starring Vikram, known for its blend of crime drama and commercial entertainment.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5094f6b408190a5a26b1a82e4a02b completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8a01d8b888190a9137b104f0e0c0c completed April 10, 2026, 7 a.m.
NEDg Description generation batch_69d8a43ba5448190ae666168ea731e4f completed April 10, 2026, 7:18 a.m.
NED2 Entity disambiguation (via description) batch_69d8a62a0e58819093a6f809585f5010 completed April 10, 2026, 7:26 a.m.
Created at: April 6, 2026, 12:21 p.m.