Triple

T19368814
Position Surface form Disambiguated ID Type / Status
Subject Emirate of Bari E484475 entity
Predicate notableRuler P22 FINISHED
Object Sawdan
Sawdan was a 9th-century Muslim ruler best known as the last emir of the Emirate of Bari in southern Italy before its conquest by Christian forces.
 E1372284 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: Sawdan | Statement: [Emirate of Bari, notableRuler, Sawdan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sawdan
Context triple: [Emirate of Bari, notableRuler, Sawdan]
  • A. Daudin
    Daudin is a French surname most notably associated with François Marie Daudin, an 18th-century zoologist and herpetologist.
  • B. Sadan
    Sadan is a subgroup of Eastern Hindi dialects spoken primarily in parts of northern and eastern India.
  • C. Sulamani
    Sulamani was a top-class Thoroughbred racehorse known for winning major international turf races in Europe and North America in the early 2000s.
  • D. Saʼdan
    Saʼdan is an Austronesian language spoken by the Toraja people of South Sulawesi, Indonesia.
  • E. Sawa
    Sawa is a Japanese surname most prominently associated with Homare Sawa, a legendary Japanese women’s footballer and World Cup winner.
  • 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: Sawdan
Triple: [Emirate of Bari, notableRuler, Sawdan]
Generated description
Sawdan was a 9th-century Muslim ruler best known as the last emir of the Emirate of Bari in southern Italy before its conquest by Christian forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sawdan
Target entity description: Sawdan was a 9th-century Muslim ruler best known as the last emir of the Emirate of Bari in southern Italy before its conquest by Christian forces.
  • A. Daudin
    Daudin is a French surname most notably associated with François Marie Daudin, an 18th-century zoologist and herpetologist.
  • B. Sadan
    Sadan is a subgroup of Eastern Hindi dialects spoken primarily in parts of northern and eastern India.
  • C. Sulamani
    Sulamani was a top-class Thoroughbred racehorse known for winning major international turf races in Europe and North America in the early 2000s.
  • D. Saʼdan
    Saʼdan is an Austronesian language spoken by the Toraja people of South Sulawesi, Indonesia.
  • E. Sawa
    Sawa is a Japanese surname most prominently associated with Homare Sawa, a legendary Japanese women’s footballer and World Cup winner.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619ae6838819080584d60cbd58bbd completed April 20, 2026, 12:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07241692fc81909b627d1939165823 completed May 15, 2026, 1:48 p.m.
NEDg Description generation batch_6a0725e546488190988000d77c961c0f completed May 15, 2026, 1:55 p.m.
NED2 Entity disambiguation (via description) batch_6a0726a79b308190a584bc808f4b2faa completed May 15, 2026, 1:59 p.m.
Created at: April 10, 2026, 1:35 p.m.