Triple

T7851303
Position Surface form Disambiguated ID Type / Status
Subject Henri La Fontaine E182059 entity
Predicate familyName P18 FINISHED
Object La Fontaine E190367 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: La Fontaine | Statement: [Henri La Fontaine, familyName, La Fontaine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: La Fontaine
Context triple: [Henri La Fontaine, familyName, La Fontaine]
  • A. La Fontaine
    La Fontaine is a residential neighborhood in the municipality of Chêne-Bougeries, located in the canton of Geneva, Switzerland.
  • B. Paul Scarron
    Paul Scarron was a 17th-century French poet, dramatist, and novelist known for his burlesque works and as the first husband of Françoise d’Aubigné, later Madame de Maintenon.
  • C. Jean-François Marmontel
    Jean-François Marmontel was an 18th-century French historian, writer, and Encyclopédiste known for his moral tales and contributions to the Enlightenment.
  • D. Jean de La Fontaine chosen
    Jean de La Fontaine was a 17th-century French poet and fabulist best known for his enduring collection of moral fables inspired by Aesop.
  • E. Honoré d’Urfé
    Honoré d’Urfé was a French novelist and nobleman best known for his influential early 17th-century pastoral romance "L'Astrée."
  • 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_69ca82869ee08190b8f9040dbc2c0467 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb18eaac508190bf373b1d50b52e1e completed March 31, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b0d95748190a202258214dda2ae completed March 31, 2026, 5:26 a.m.
Created at: March 30, 2026, 4:50 p.m.