Triple

T3545907
Position Surface form Disambiguated ID Type / Status
Subject María Cortés E74995 entity
Predicate givenName P17 FINISHED
Object María E65513 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: María | Statement: [María Cortés, givenName, María]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: María
Context triple: [María Cortés, givenName, María]
  • A. María chosen
    María is a key character in Ernest Hemingway's novel "For Whom the Bell Tolls," known as a young Spanish woman and love interest of the protagonist amid the Spanish Civil War.
  • B. María
    "María" is a film featuring actress Taryn Power in a significant role.
  • C. Luisa
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • D. Francisca
    Francisca is a feminine given name, used in various European and Latin American cultures, that is cognate with the English name Frances.
  • E. Manuela
    Manuela is the given name of Maria Manuela, a 16th-century Portuguese princess who became Queen of Castile through marriage to King Philip II of Spain.
  • 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_69ad85d33c6c819081d5ac1df13b5680 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbf77d938819095c72a88b5af644a completed March 8, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b38be29b408190a8dba8c8ae2485a4 completed March 13, 2026, 4 a.m.
Created at: March 8, 2026, 3:20 p.m.