Triple

T22877776
Position Surface form Disambiguated ID Type / Status
Subject Merdeka Palace E567372 entity
Predicate nearby P350 FINISHED
Object Jakarta Cathedral 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: Jakarta Cathedral | Statement: [Merdeka Palace, nearby, Jakarta Cathedral]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jakarta Cathedral
Context triple: [Merdeka Palace, nearby, Jakarta Cathedral]
  • A. Jakarta Cathedral chosen
    Jakarta Cathedral is a prominent neo-Gothic Roman Catholic church and historic religious landmark located in Indonesia’s capital city.
  • B. Ruteng Cathedral
    Ruteng Cathedral is a prominent Roman Catholic church and landmark located in the town of Ruteng on Flores Island, Indonesia.
  • C. Aya Yani Church
    Aya Yani Church is a historic Greek Orthodox church located on Burgazada, one of Istanbul’s Princes’ Islands.
  • D. Jakarta City Hall
    Jakarta City Hall is the main administrative headquarters and office complex of the Jakarta provincial government in Indonesia.
  • E. Grand Mosque of Bandung
    The Grand Mosque of Bandung is a prominent Islamic place of worship and historical landmark in Bandung, Indonesia, known for its large domes, twin minarets, and central role in the city’s religious and civic life.
  • 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_69e24589d8348190b96422d13a678bc1 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17f5966c08190a9ded9b19b166112 completed April 29, 2026, 3:47 a.m.
Created at: April 17, 2026, 3:39 p.m.