Triple

T17685287
Position Surface form Disambiguated ID Type / Status
Subject Colon Street E440872 entity
Predicate hasNearbyLandmark P2064 FINISHED
Object Cebu City Hall 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: Cebu City Hall | Statement: [Colon Street, hasNearbyLandmark, Cebu City Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cebu City Hall
Context triple: [Colon Street, hasNearbyLandmark, Cebu City Hall]
  • A. Cebu City Hall chosen
    Cebu City Hall is the main government building and administrative center of Cebu City in the Philippines.
  • B. Quezon City Hall
    Quezon City Hall is the main government complex and administrative center of Quezon City in Metro Manila, Philippines.
  • C. Cavite City Hall
    Cavite City Hall is the main government building and administrative center of Cavite City in the Philippines.
  • D. Manila City Hall
    Manila City Hall is a prominent government building and historical landmark in the Philippines’ capital, known for its distinctive clock tower and its location at the site of intense fighting during the 1945 Battle of Manila.
  • E. Makati City Hall
    Makati City Hall is the main government building and administrative center of Makati, a major financial and business district in Metro Manila, Philippines.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47047d90c8190a172201f3de6db87 completed April 19, 2026, 6:03 a.m.
Created at: April 10, 2026, 10:02 a.m.