Triple

T8719653
Position Surface form Disambiguated ID Type / Status
Subject Quasimodo E206979 entity
Predicate adoptedBy P1034 FINISHED
Object Claude Frollo E207258 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: Claude Frollo | Statement: [Quasimodo, adoptedBy, Claude Frollo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Claude Frollo
Context triple: [Quasimodo, adoptedBy, Claude Frollo]
  • A. Claude Frollo chosen
    Claude Frollo is the obsessive and morally conflicted archdeacon of Notre-Dame who serves as the primary antagonist in Victor Hugo’s novel "The Hunchback of Notre-Dame."
  • B. Godfrey the Hunchback
    Godfrey the Hunchback was an 11th-century Duke of Lower Lorraine and prominent nobleman of the Holy Roman Empire, noted for his political influence and turbulent marriage to Matilda of Tuscany.
  • C. Bernard de Marigny
    Bernard de Marigny was a prominent early-19th-century New Orleans landowner, politician, and gambler best known for developing the Faubourg Marigny neighborhood.
  • D. Quasimodo
    Quasimodo is the deformed and kind-hearted bell ringer of Notre-Dame Cathedral in Victor Hugo’s novel "The Hunchback of Notre-Dame."
  • E. Arnaud de Puyfontaine
    Arnaud de Puyfontaine is a French media executive best known as the chief executive officer of Vivendi.
  • 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_69ca835811d8819081ea00fd2a2c9a1c completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d02a52c81909f93622ae6920b80 completed March 31, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf28ec7148819096f7fa33e4588b62 completed April 3, 2026, 2:41 a.m.
Created at: March 30, 2026, 6:36 p.m.