Triple

T12464704
Position Surface form Disambiguated ID Type / Status
Subject Castello di Lombardia E297891 entity
Predicate previousFortificationOnSite P105147 FINISHED
Object Byzantine fortress 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: Byzantine fortress | Statement: [Castello di Lombardia, previousFortificationOnSite, Byzantine fortress]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousFortificationOnSite
Context triple: [Castello di Lombardia, previousFortificationOnSite, Byzantine fortress]
  • A. fortifiedSite
    Indicates a site that has been strengthened or defended with protective structures or measures against attack.
  • B. previousGarrison
    Indicates that one entity served as the earlier or former garrison location or stationed force for another entity.
  • C. wasFortifiedBy
    Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
  • D. usedFortificationsAt
    Indicates that an entity employed or deployed specific fortifications in a particular context, such as a battle, campaign, or defensive situation.
  • E. fortressOriginallyBuiltBy
    Indicates that a particular fortress was initially constructed by a specified builder or group.
  • F. None of above. chosen

Provenance (4 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_69d6ada270808190b1a2b2e7b02bb426 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94e626dbc8190ac7dcdb542ba9b0c completed April 10, 2026, 7:24 p.m.
PD Predicate disambiguation batch_69d94d3f701c81909dd0e00251ac8553 completed April 10, 2026, 7:19 p.m.
PDg Predicate description generation batch_69d94e5f8d04819086d1ad4d62364005 completed April 10, 2026, 7:24 p.m.
Created at: April 8, 2026, 9:56 p.m.