Triple

T22642400
Position Surface form Disambiguated ID Type / Status
Subject Teatro de Santa Isabel E558863 entity
Predicate namedAfter P63 FINISHED
Object Saint Isabel 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: Saint Isabel | Statement: [Teatro de Santa Isabel, namedAfter, Saint Isabel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint Isabel
Context triple: [Teatro de Santa Isabel, namedAfter, Saint Isabel]
  • A. Saint Isabel chosen
    Saint Isabel is a Christian saint traditionally associated with charity, humility, and service to the poor, venerated in various regions that bear her name.
  • B. Santa Isabel
    Santa Isabel is a supermarket chain in Latin America operated under the retail group Cencosud.
  • C. Santa Isabel
    Santa Isabel is a municipality in the state of São Paulo, Brazil, known for its preserved natural areas and role as part of the greater São Paulo region.
  • D. Santa Isabel
    Santa Isabel is a Santiago Metro station on Line 5 located in the central area of Chile’s capital city.
  • E. Santa Isabel
    Santa Isabel is an urban neighborhood within the Carabayllo district of Lima, Peru.
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1703489a48190bd97a7eb7a571b64 completed April 29, 2026, 2:43 a.m.
Created at: April 17, 2026, 3:04 p.m.