Triple

T5236059
Position Surface form Disambiguated ID Type / Status
Subject Exeter Book E118223 entity
Predicate content P4446 FINISHED
Object Deor E503407 NE FINISHED

How this triple was built (2 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: Deor | Statement: [Exeter Book, content, Deor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deor
Context triple: [Exeter Book, content, Deor]
  • A. Deor chosen
    Deor is an Old English elegiac poem in which a scop reflects on personal misfortune and the transience of suffering by recalling legendary hardships that eventually passed.
  • B. Alfrid
    Alfrid is a masculine given name of Germanic origin, commonly associated with medieval and fantasy settings.
  • C. Wulf
    Wulf is the given name of Wulf Wolodia Grajonca, better known as the American singer and songwriter Bill Graham.
  • D. Godric of Mappestone
    Godric of Mappestone was a Norman-era nobleman and landholder in Herefordshire, England, known as the medieval lord responsible for establishing Goodrich Castle.
  • E. Ceolwulf I of Mercia
    Ceolwulf I of Mercia was a 9th-century Anglo-Saxon king who briefly ruled the powerful kingdom of Mercia during a period of political instability in early medieval England.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4467db0881909b3b0982df32cc8f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b2595c88190b4ca0b99c2f31472 completed March 20, 2026, 4:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69bef81cca948190ab00302787367f43 completed March 21, 2026, 7:57 p.m.
Created at: March 20, 2026, 1:49 p.m.