Triple

T9525984
Position Surface form Disambiguated ID Type / Status
Subject Reculver, Kent E229760 entity
Predicate wasRomanName P6662 FINISHED
Object Regulbium
Regulbium was the Roman-era coastal fort and settlement that later became known as Reculver in Kent, England.
 E806165 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: Regulbium | Statement: [Reculver, Kent, wasRomanName, Regulbium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Regulbium
Context triple: [Reculver, Kent, wasRomanName, Regulbium]
  • A. Albium Ingaunum
    Albium Ingaunum was an important ancient Ligurian coastal city, located in what is now Albenga on the Italian Riviera.
  • B. Ormenium
    Ormenium was an ancient town in the region of Magnesia in Thessaly, Greece, known from classical sources such as Homer’s Iliad.
  • C. Agyrium
    Agyrium was an ancient city in central Sicily, historically significant as the birthplace of the Greek historian Diodorus Siculus.
  • D. Samnium
    Samnium was an ancient region of south-central Italy inhabited by the Samnites, an Oscan-speaking Italic people known for their wars with the Roman Republic.
  • E. Tauresium
    Tauresium was an ancient settlement in the Balkans, traditionally identified as the birthplace of the Byzantine emperor Justinian I.
  • 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: Regulbium
Triple: [Reculver, Kent, wasRomanName, Regulbium]
Generated description
Regulbium was the Roman-era coastal fort and settlement that later became known as Reculver in Kent, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Regulbium
Target entity description: Regulbium was the Roman-era coastal fort and settlement that later became known as Reculver in Kent, England.
  • A. Albium Ingaunum
    Albium Ingaunum was an important ancient Ligurian coastal city, located in what is now Albenga on the Italian Riviera.
  • B. Ormenium
    Ormenium was an ancient town in the region of Magnesia in Thessaly, Greece, known from classical sources such as Homer’s Iliad.
  • C. Agyrium
    Agyrium was an ancient city in central Sicily, historically significant as the birthplace of the Greek historian Diodorus Siculus.
  • D. Samnium
    Samnium was an ancient region of south-central Italy inhabited by the Samnites, an Oscan-speaking Italic people known for their wars with the Roman Republic.
  • E. Tauresium
    Tauresium was an ancient settlement in the Balkans, traditionally identified as the birthplace of the Byzantine emperor Justinian I.
  • 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_69ca847870a881909d8d751a7d29da39 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd989b529c81909ee18dd3d468c816 completed April 1, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69d14c2710b481909a13d946f6dd5b2d completed April 4, 2026, 5:36 p.m.
NEDg Description generation batch_69d14e49c97481909a1bab1b4d482194 completed April 4, 2026, 5:45 p.m.
NED2 Entity disambiguation (via description) batch_69d14ee1fcdc8190bf23a3af97f0ba39 completed April 4, 2026, 5:48 p.m.
Created at: March 30, 2026, 7:59 p.m.