Triple

T10164282
Position Surface form Disambiguated ID Type / Status
Subject Sisebut E233967 entity
Predicate predecessor P97 FINISHED
Object Gundemar
Gundemar was a 7th-century Visigothic king of Hispania and Septimania who ruled briefly before being succeeded by Sisebut.
 E845660 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: Gundemar | Statement: [Sisebut, predecessor, Gundemar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gundemar
Context triple: [Sisebut, predecessor, Gundemar]
  • A. Reginherus
    Reginherus is a Germanic personal name, historically related to and cognate with the legendary Norse name Ragnar.
  • B. Thankmar
    Thankmar was a 10th-century German nobleman and the eldest son of King Henry the Fowler, whose disputed legitimacy led to his rebellion against his half-brother Otto I.
  • C. Wulfram
    Wulfram is an alternative spelling or variant form of the name Wolfram, which is associated with both a given name and the chemical element tungsten.
  • D. Willigis
    Willigis was a powerful 10th-century German churchman and statesman who rose from humble origins to become one of the most influential political and ecclesiastical figures of the Holy Roman Empire.
  • E. Reimund
    Reimund is a masculine given name, primarily used in German-speaking regions, that is a variant of the name Raymond.
  • 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: Gundemar
Triple: [Sisebut, predecessor, Gundemar]
Generated description
Gundemar was a 7th-century Visigothic king of Hispania and Septimania who ruled briefly before being succeeded by Sisebut.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gundemar
Target entity description: Gundemar was a 7th-century Visigothic king of Hispania and Septimania who ruled briefly before being succeeded by Sisebut.
  • A. Reginherus
    Reginherus is a Germanic personal name, historically related to and cognate with the legendary Norse name Ragnar.
  • B. Thankmar
    Thankmar was a 10th-century German nobleman and the eldest son of King Henry the Fowler, whose disputed legitimacy led to his rebellion against his half-brother Otto I.
  • C. Wulfram
    Wulfram is an alternative spelling or variant form of the name Wolfram, which is associated with both a given name and the chemical element tungsten.
  • D. Willigis
    Willigis was a powerful 10th-century German churchman and statesman who rose from humble origins to become one of the most influential political and ecclesiastical figures of the Holy Roman Empire.
  • E. Reimund
    Reimund is a masculine given name, primarily used in German-speaking regions, that is a variant of the name Raymond.
  • 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_69ca848e80748190b91d1e04d35512c7 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec6b96dc8190ae37d0d28e4c393b completed April 2, 2026, 4:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d300d672fc8190ad5b937d02a737fd completed April 6, 2026, 12:39 a.m.
NEDg Description generation batch_69d30254aabc8190966a4398c59a851e completed April 6, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69d30305924c8190998cbefa372dca9a completed April 6, 2026, 12:49 a.m.
Created at: March 30, 2026, 9:09 p.m.