Triple

T20379828
Position Surface form Disambiguated ID Type / Status
Subject Castello di Arechi E497794 entity
Predicate namedAfter P63 FINISHED
Object Arechi II
Arechi II was an 8th-century Lombard prince of Benevento known for consolidating his rule in southern Italy and fortifying the region against Byzantine and Frankish influence.
E1426574 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: Arechi II | Statement: [Castello di Arechi, namedAfter, Arechi II]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arechi II
Context triple: [Castello di Arechi, namedAfter, Arechi II]
  • A. Yasuko
    Yasuko is a feminine Japanese given name commonly used for women.
  • B. Iyesato
    Iyesato is the given name of Prince Iyesato Tokugawa, a prominent Japanese noble and political leader of the early 20th century.
  • C. Kujō Asako
    Kujō Asako is a member of the prominent Japanese aristocratic Kujō family, historically part of the influential Fujiwara clan.
  • D. Toyotomi Naahime
    Toyotomi Naahime was a daughter of Toyotomi Hideyori and a member of the late Sengoku-period Toyotomi clan in Japan.
  • E. Fujiwara Nanke
    Fujiwara Nanke was one of the four main houses of Japan’s powerful Fujiwara clan, influential in Heian-period court politics and aristocratic society.
  • 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: Arechi II
Triple: [Castello di Arechi, namedAfter, Arechi II]
Generated description
Arechi II was an 8th-century Lombard prince of Benevento known for consolidating his rule in southern Italy and fortifying the region against Byzantine and Frankish influence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Arechi II
Target entity description: Arechi II was an 8th-century Lombard prince of Benevento known for consolidating his rule in southern Italy and fortifying the region against Byzantine and Frankish influence.
  • A. Yasuko
    Yasuko is a feminine Japanese given name commonly used for women.
  • B. Iyesato
    Iyesato is the given name of Prince Iyesato Tokugawa, a prominent Japanese noble and political leader of the early 20th century.
  • C. Kujō Asako
    Kujō Asako is a member of the prominent Japanese aristocratic Kujō family, historically part of the influential Fujiwara clan.
  • D. Toyotomi Naahime
    Toyotomi Naahime was a daughter of Toyotomi Hideyori and a member of the late Sengoku-period Toyotomi clan in Japan.
  • E. Fujiwara Nanke
    Fujiwara Nanke was one of the four main houses of Japan’s powerful Fujiwara clan, influential in Heian-period court politics and aristocratic society.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b026e081909541e545886c8380 completed April 20, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a087095286c8190afdcb855220526fc completed May 16, 2026, 1:26 p.m.
NEDg Description generation batch_6a087129ce3c8190a67ac34ec697ad31 completed May 16, 2026, 1:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0871e3573c81908216b5e508374081 completed May 16, 2026, 1:32 p.m.
Created at: April 16, 2026, 11:27 a.m.