Triple

T16167185
Position Surface form Disambiguated ID Type / Status
Subject Sergio Osmeña E392334 entity
Predicate child P120 FINISHED
Object Maria Luisa Osmeña E392334 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: Maria Luisa Osmeña | Statement: [Sergio Osmeña, child, Maria Luisa Osmeña]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria Luisa Osmeña
Context triple: [Sergio Osmeña, child, Maria Luisa Osmeña]
  • A. Maria Luisa Osmeña chosen
    Maria Luisa Osmeña was a daughter of Philippine President Sergio Osmeña and a member of the prominent Osmeña political family.
  • B. Josefina Osmeña
    Josefina Osmeña was a daughter of Philippine President Sergio Osmeña and a member of the prominent Osmeña political family.
  • C. Consuelo Osmeña
    Consuelo Osmeña was a member of the prominent Osmeña political family of the Philippines, known primarily as a daughter of former President Sergio Osmeña.
  • D. Francisca Reyes-Aquino
    Francisca Reyes-Aquino was a pioneering Filipino folk dance researcher and educator who helped document and popularize traditional Philippine dances.
  • E. Maria Eugenia
    Maria Eugenia is a Spanish infanta, a princess of the royal family 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21eb3ec4c81908d4e5c0f39a85900 completed April 17, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffef96a088190a1c1728288a9c4ef completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 5:02 a.m.