Triple

T13677899
Position Surface form Disambiguated ID Type / Status
Subject Pierre Corneille E327922 entity
Predicate notableWork P4 FINISHED
Object Médée E234814 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: Médée | Statement: [Pierre Corneille, notableWork, Médée]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Médée
Context triple: [Pierre Corneille, notableWork, Médée]
  • A. Creusa
    Creusa is a figure in Greek mythology, often depicted as an Athenian princess and mother of Ion in Euripides’ tragedy.
  • B. Creusa
    Creusa is a figure in Greek mythology, best known as a Trojan princess and the wife of the hero Aeneas.
  • C. Lycomède
    Lycomède is a character from Greek mythology, traditionally depicted as a king associated with the stories surrounding Achilles and other heroic figures.
  • D. Anticlea
    Anticlea is a figure in Greek mythology best known as the mother of the hero Odysseus and the wife of Laertes.
  • E. Glauce chosen
    Glauce is a figure in Greek mythology, a Corinthian princess whom Jason marries after leaving Medea, leading to Medea’s infamous revenge.
  • 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_69d8076f1fa8819094664a59b55010df completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc65d8dc081909664e69bb38610ba completed April 12, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f794405a38819085f38170c56564f2 completed May 3, 2026, 6:30 p.m.
Created at: April 9, 2026, 9:53 p.m.