Triple

T8925300
Position Surface form Disambiguated ID Type / Status
Subject Cohors I Tungrorum E212524 entity
Predicate ethnicComposition P1898 FINISHED
Object Tungrian
The Tungrians were an ancient Germanic people from the region of modern-day Belgium who served as auxiliaries in the Roman army and gave their name to the civitas Tungrorum.
E766714 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: Tungrian | Statement: [Cohors I Tungrorum, ethnicComposition, Tungrian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tungrian
Context triple: [Cohors I Tungrorum, ethnicComposition, Tungrian]
  • A. Segestani
    The Segestani were an ancient Illyrian tribe that inhabited the region around the city of Siscia in what is now central Croatia.
  • B. Ripuarian
    Ripuarian is a group of closely related West Central German dialects spoken primarily in the Cologne region and surrounding areas along the Rhine.
  • C. Turiysk
    Turiysk is a small town in western Ukraine known for its historical roots and location within the Volyn region.
  • D. Dargin
    Dargin is a Northeast Caucasian language spoken primarily by the Dargin people in the Republic of Dagestan in Russia.
  • E. Tangut
    Tangut is an extinct Tibeto-Burman language once used in the Western Xia dynasty, best known today for its large and complex logographic writing system.
  • 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: Tungrian
Triple: [Cohors I Tungrorum, ethnicComposition, Tungrian]
Generated description
The Tungrians were an ancient Germanic people from the region of modern-day Belgium who served as auxiliaries in the Roman army and gave their name to the civitas Tungrorum.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tungrian
Target entity description: The Tungrians were an ancient Germanic people from the region of modern-day Belgium who served as auxiliaries in the Roman army and gave their name to the civitas Tungrorum.
  • A. Segestani
    The Segestani were an ancient Illyrian tribe that inhabited the region around the city of Siscia in what is now central Croatia.
  • B. Ripuarian
    Ripuarian is a group of closely related West Central German dialects spoken primarily in the Cologne region and surrounding areas along the Rhine.
  • C. Turiysk
    Turiysk is a small town in western Ukraine known for its historical roots and location within the Volyn region.
  • D. Dargin
    Dargin is a Northeast Caucasian language spoken primarily by the Dargin people in the Republic of Dagestan in Russia.
  • E. Tangut
    Tangut is an extinct Tibeto-Burman language once used in the Western Xia dynasty, best known today for its large and complex logographic writing system.
  • 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_69ca839481d48190b42b037e0d0f636c completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66700fb48190874563e535f20437 completed April 1, 2026, 12:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba58e9ec81909141c516d05ac790 completed April 3, 2026, 1:02 p.m.
NEDg Description generation batch_69cfbade9330819096d4b0eeacdad6da completed April 3, 2026, 1:04 p.m.
NED2 Entity disambiguation (via description) batch_69cfbec2b8888190a0390168fdcef05f completed April 3, 2026, 1:21 p.m.
Created at: March 30, 2026, 6:57 p.m.