Triple

T15002068
Position Surface form Disambiguated ID Type / Status
Subject Horses of Saint Mark E374114 entity
Predicate formerDisplayLocation P55436 FINISHED
Object façade of St. Mark's Basilica LITERAL 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: façade of St. Mark's Basilica | Statement: [Horses of Saint Mark, formerDisplayLocation, façade of St. Mark's Basilica]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerDisplayLocation
Context triple: [Horses of Saint Mark, formerDisplayLocation, façade of St. Mark's Basilica]
  • A. formerlyKnownLocationAs
    Indicates that an entity was previously known or referred to by a different location name or designation.
  • B. formerlyLocatedOn chosen
    Indicates that an entity was once located on or situated upon another entity, but is no longer in that position.
  • C. locatedAtFormer
    Indicates that an entity is currently located at a place where another entity was previously located.
  • D. formerSiteOf
    Indicates that a location previously hosted or contained something (such as a structure, organization, or event) that is no longer present there.
  • E. previousLocationName
    Indicates that one entity specifies the name of a location where another entity was situated or occurred before its current location.
  • F. None of above.

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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded72fec948190b1c9705538c57976 completed April 15, 2026, 12:09 a.m.
PD Predicate disambiguation batch_69de9a6531a88190acde65199a477350 completed April 14, 2026, 7:49 p.m.
Created at: April 10, 2026, 2:54 a.m.