Triple

T19978520
Position Surface form Disambiguated ID Type / Status
Subject Heorogar E493753 entity
Predicate offspring P980 FINISHED
Object Heoroweard NE NERFINISHED

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: Heoroweard | Statement: [Heorogar, offspring, Heoroweard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heoroweard
Context triple: [Heorogar, offspring, Heoroweard]
  • A. Heoroweard chosen
    Heoroweard is a minor figure in the Old English epic tradition, known primarily as a relative of the Danish royal house mentioned in Beowulf.
  • B. Deor
    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.
  • C. Wulf
    Wulf is the given name of Wulf Wolodia Grajonca, better known as the American singer and songwriter Bill Graham.
  • D. Alfrid
    Alfrid is a masculine given name of Germanic origin, commonly associated with medieval and fantasy settings.
  • E. Godwyn
    Godwyn is a central character in Ken Follett’s historical novel "World Without End," whose life and actions significantly influence the political and social dynamics of the town of Kingsbridge.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d11108481908241a2a96a795a7d completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:27 p.m.