Triple

T17016943
Position Surface form Disambiguated ID Type / Status
Subject Loi Ejercito E412844 entity
Predicate hasChild P369 FINISHED
Object Jinggoy Estrada NE NERFINISHED

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: Jinggoy Estrada | Statement: [Loi Ejercito, hasChild, Jinggoy Estrada]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jinggoy Estrada
Context triple: [Loi Ejercito, hasChild, Jinggoy Estrada]
  • A. Jinggoy Estrada
    Jinggoy Estrada is a Filipino politician and actor who has served as a senator of the Philippines and is the son of former president Joseph Estrada.
  • B. Jinggoy Ejercito Estrada chosen
    Jinggoy Ejercito Estrada is a Filipino politician and actor who has served as a senator of the Philippines and is the son of former president Joseph Estrada.
  • C. Cesar Montano
    Cesar Montano is a Filipino actor and filmmaker known for his prominent roles in Philippine cinema and appearances in international war films.
  • D. Don Juan Panganiban
    Don Juan Panganiban is a character in the Ilocano epic "Biag ni Lam-ang," known as one of the notable figures surrounding the hero Lam-ang’s adventures.
  • E. Jesus Sablan
    Jesus Sablan is a Northern Mariana Islands politician who served as lieutenant governor of the U.S. Commonwealth in the western Pacific.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d47fec248190bf261cac920291b1 completed April 18, 2026, 6:59 p.m.
Created at: April 10, 2026, 5:33 a.m.