Triple

T16904653
Position Surface form Disambiguated ID Type / Status
Subject Hedwig of Denmark E424527 entity
Predicate givenName P17 FINISHED
Object Hedwig E1235233 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: Hedwig | Statement: [Hedwig of Denmark, givenName, Hedwig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hedwig
Context triple: [Hedwig of Denmark, givenName, Hedwig]
  • A. Hedwig
    Hedwig is the birth name of Hedy Lamarr, the Austrian-born Hollywood actress and inventor known for pioneering frequency-hopping technology.
  • B. Hedwig
    Hedwig is traditionally known as the wife of the legendary Swiss folk hero William Tell in Swiss folklore.
  • C. Hedwig
    Hedwig is the flamboyant, genderqueer rock singer and central character of the cult musical and film "Hedwig and the Angry Inch."
  • D. Hedwig chosen
    Hedwig is a feminine given name of Germanic origin, historically borne by several European noblewomen and saints.
  • E. Hedwig (Harry Potter character)
    Hedwig is Harry Potter’s loyal snowy owl companion, known for delivering his mail and symbolizing his connection to the wizarding world.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8df454c8190898ebdd75985e51c completed April 18, 2026, 6:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7b47a6081909d8609c2bce96d1a completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:30 a.m.