Triple

T17699121
Position Surface form Disambiguated ID Type / Status
Subject Rainulf Drengot E441248 entity
Predicate familyName P18 FINISHED
Object Drengot
Drengot was a prominent Norman noble family that played a key role in the conquest and political shaping of southern Italy in the 11th century.
 E1282678 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: Drengot | Statement: [Rainulf Drengot, familyName, Drengot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Drengot
Context triple: [Rainulf Drengot, familyName, Drengot]
  • A. Tegüder
    Tegüder (also known as Ahmad Tegüder) was a 13th-century Ilkhanid ruler of Persia who converted to Islam and briefly reigned as a Mongol khan.
  • B. Dulo
    Dulo was the early medieval ruling dynasty of the Bulgars, traditionally associated with Khan Asparuh and the founding of the First Bulgarian Empire.
  • C. Heimirich
    Heimirich is a Germanic given name of ancient origin, from which the modern name Heinrich is derived.
  • D. Berhtwald
    Berhtwald was an early 8th-century Archbishop of Canterbury who played a key role in consolidating the English Church after the reforms of Theodore of Tarsus.
  • E. Shvarn
    Shvarn was a 13th-century prince of the Kingdom of Galicia–Volhynia who briefly ruled as Grand Duke of Lithuania.
  • 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: Drengot
Triple: [Rainulf Drengot, familyName, Drengot]
Generated description
Drengot was a prominent Norman noble family that played a key role in the conquest and political shaping of southern Italy in the 11th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Drengot
Target entity description: Drengot was a prominent Norman noble family that played a key role in the conquest and political shaping of southern Italy in the 11th century.
  • A. Tegüder
    Tegüder (also known as Ahmad Tegüder) was a 13th-century Ilkhanid ruler of Persia who converted to Islam and briefly reigned as a Mongol khan.
  • B. Dulo
    Dulo was the early medieval ruling dynasty of the Bulgars, traditionally associated with Khan Asparuh and the founding of the First Bulgarian Empire.
  • C. Heimirich
    Heimirich is a Germanic given name of ancient origin, from which the modern name Heinrich is derived.
  • D. Berhtwald
    Berhtwald was an early 8th-century Archbishop of Canterbury who played a key role in consolidating the English Church after the reforms of Theodore of Tarsus.
  • E. Shvarn
    Shvarn was a 13th-century prince of the Kingdom of Galicia–Volhynia who briefly ruled as Grand Duke of Lithuania.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47158be9c8190bbf4e5162ff74ad2 completed April 19, 2026, 6:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0223365be08190992b1e80553aebcc completed May 11, 2026, 6:43 p.m.
NEDg Description generation batch_6a0224af2c7c819095b771014f36d0e4 completed May 11, 2026, 6:49 p.m.
NED2 Entity disambiguation (via description) batch_6a02259ef96881909660d18a4a149f8f completed May 11, 2026, 6:53 p.m.
Created at: April 10, 2026, 10:04 a.m.