Triple

T12963935
Position Surface form Disambiguated ID Type / Status
Subject Malate, Manila E321215 entity
Predicate hasLandmark P105 FINISHED
Object Malate Church E261765 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: Malate Church | Statement: [Malate, Manila, hasLandmark, Malate Church]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malate Church
Context triple: [Malate, Manila, hasLandmark, Malate Church]
  • A. Malate Church chosen
    Malate Church is a historic Spanish-era Roman Catholic church in the Malate district of Manila, Philippines, known for its baroque architecture and prominent location facing Manila Bay.
  • B. Church of the Agony
    The Church of the Agony is a Roman Catholic basilica on the Mount of Olives in Jerusalem, traditionally believed to mark the place where Jesus prayed in anguish before his arrest.
  • C. Calvary Church
    Calvary Church is a historic Christian church located in the Gramercy neighborhood of Manhattan, New York City.
  • D. Saul Church
    Saul Church is a historic Christian church in Saul, County Down, Northern Ireland, traditionally associated with Saint Patrick and early Irish Christianity.
  • E. Tagogi Church
    Tagogi Church is a historic Christian church located in the mountainous Khulo region of southwestern Georgia.
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e30b7e88190ac07c91147b62d16 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8e227948190a2d08db97b4e41aa completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:25 p.m.