Triple

T25074317
Position Surface form Disambiguated ID Type / Status
Subject Diocese of Trieste E628004 entity
Predicate hasHistoricCathedral P108426 FINISHED
Object San Giusto
San Giusto is the historic cathedral of Trieste, Italy, renowned for its Romanesque-Gothic architecture and prominent hilltop position overlooking the city and Gulf of Trieste.
 E1664307 NE FINISHED

How this triple was built (3 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: San Giusto | Statement: [Diocese of Trieste, hasHistoricCathedral, San Giusto]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: San Giusto
Triple: [Diocese of Trieste, hasHistoricCathedral, San Giusto]
Generated description
San Giusto is the historic cathedral of Trieste, Italy, renowned for its Romanesque-Gothic architecture and prominent hilltop position overlooking the city and Gulf of Trieste.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasHistoricCathedral
Context triple: [Diocese of Trieste, hasHistoricCathedral, San Giusto]
  • A. hasCathedralTown
    Indicates that a given town is recognized as having a cathedral, typically serving as the seat of a bishop or central church authority.
  • B. hasHistoricChurches
    Indicates that an entity possesses or contains one or more churches of recognized historical significance.
  • C. hasCathedralStatusSince
    Indicates the point in time from which something has held the official status of a cathedral.
  • D. hasCathedralCity
    Indicates that a particular city is officially recognized as the cathedral city associated with a given ecclesiastical jurisdiction or region.
  • E. hasCatholicCathedral chosen
    Indicates that a place or jurisdiction possesses at least one officially recognized Catholic cathedral within its boundaries.
  • F. None of above.

Provenance (6 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_69e2ff2d71dc8190b4758e57d643cbe4 completed April 18, 2026, 3:49 a.m.
NER Named-entity recognition batch_69f657f653448190a945b4751af8507d completed May 2, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1048de294c8190897bdd9107d961eb completed May 22, 2026, 12:15 p.m.
NEDg Description generation batch_6a104c1f2e448190b0ee1a8c0bca7520 completed May 22, 2026, 12:29 p.m.
NED2 Entity disambiguation (via description) batch_6a104d107b088190aad51efff7bcef1e completed May 22, 2026, 12:33 p.m.
PD Predicate disambiguation batch_69f6575ba12081909396036f78757a76 completed May 2, 2026, 7:58 p.m.
Created at: April 18, 2026, 6:20 a.m.