Triple

T22941804
Position Surface form Disambiguated ID Type / Status
Subject Agnes of Lusignan E569750 entity
Predicate givenName P17 FINISHED
Object Agnes 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: Agnes | Statement: [Agnes of Lusignan, givenName, Agnes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agnes
Context triple: [Agnes of Lusignan, givenName, Agnes]
  • A. Agnes chosen
    Agnes is a feminine given name of Greek origin meaning "pure" or "chaste," historically popular in various European cultures and Christian traditions.
  • B. Agnes
    Agnes is a character from Matthew Gregory Lewis's Gothic novel "The Monk," known for her tragic storyline involving forbidden love and persecution.
  • C. Agnes
    Agnes is the suburban alias of Agatha Harkness, a powerful witch and key antagonist in the Marvel Cinematic Universe series "WandaVision."
  • D. Agnes
    Agnes of Hesse was a 16th-century German noblewoman, Landgravine of Hesse by birth and later Electress of Saxony through marriage.
  • E. Agnes
    Agnes is a character from the Disney fantasy-comedy film "Godmothered," serving as one of the supporting figures in the story’s modern twist on fairy godmothers.
  • 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_69e24590862c8190858f180ad302adab completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181394fec81909da791bb346dbd0a completed April 29, 2026, 3:55 a.m.
Created at: April 17, 2026, 3:45 p.m.