Triple

T2055524
Position Surface form Disambiguated ID Type / Status
Subject Roman army E45664 entity
Predicate hasUnitType P6008 FINISHED
Object limitanei
The limitanei were frontier garrison troops of the later Roman Empire, stationed along borders to provide local defense and security rather than serving as highly mobile field armies.
 E228782 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: limitanei | Statement: [Roman army, hasUnitType, limitanei]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: limitanei
Context triple: [Roman army, hasUnitType, limitanei]
  • A. Misenum
    Misenum was an important ancient Roman naval base and coastal town located at the northwestern end of the Bay of Naples in Italy.
  • B. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • C. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • D. Nolano
    Nolano is the Italian demonym for a person from the town of Nola in the Campania region of southern Italy.
  • E. Mutina
    Mutina was an important ancient Roman city in northern Italy, known today as Modena.
  • 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: limitanei
Triple: [Roman army, hasUnitType, limitanei]
Generated description
The limitanei were frontier garrison troops of the later Roman Empire, stationed along borders to provide local defense and security rather than serving as highly mobile field armies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: limitanei
Target entity description: The limitanei were frontier garrison troops of the later Roman Empire, stationed along borders to provide local defense and security rather than serving as highly mobile field armies.
  • A. Misenum
    Misenum was an important ancient Roman naval base and coastal town located at the northwestern end of the Bay of Naples in Italy.
  • B. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • C. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • D. Nolano
    Nolano is the Italian demonym for a person from the town of Nola in the Campania region of southern Italy.
  • E. Mutina
    Mutina was an important ancient Roman city in northern Italy, known today as Modena.
  • 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_69a8891a19508190a12ef1e192308dcb completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9a9ce548190a5a3488fafb2e79e completed March 7, 2026, 5:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae200eb09881908bbfe47ebb62f55e completed March 9, 2026, 1:19 a.m.
NEDg Description generation batch_69ae20cb479c8190853d0d954af16887 completed March 9, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_69ae21614e74819093617a355f0857c8 completed March 9, 2026, 1:24 a.m.
Created at: March 4, 2026, 7:40 p.m.