Triple

T492533
Position Surface form Disambiguated ID Type / Status
Subject François Mitterrand E10220 entity
Predicate givenName P17 FINISHED
Object François E41603 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: François | Statement: [François Mitterrand, givenName, François]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: François
Context triple: [François Mitterrand, givenName, François]
  • A. François chosen
    François is the given name of the French poet and essayist Sully Prudhomme, the first recipient of the Nobel Prize in Literature.
  • B. Édouard
    Édouard is the French form of the given name Edward, commonly used in French-speaking countries.
  • C. Philip II of France
    Philip II of France was the Capetian king who greatly expanded French royal power and territory in the late 12th and early 13th centuries, notably at the expense of the English crown.
  • D. Alexandre
    Alexandre is a given name of Greek origin, commonly used in French and Portuguese-speaking countries as a form of Alexander.
  • E. Charles X of France
    Charles X of France was the last Bourbon king of France before the July Monarchy, whose conservative and reactionary policies led to his overthrow in the July Revolution of 1830.
  • 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f0faab4881909f65f172198b5bd2 completed Feb. 28, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4b23a3ddc8190a685a63923d1d175 completed March 1, 2026, 9:40 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.