Triple

T28846770
Position Surface form Disambiguated ID Type / Status
Subject Sanctuary of Aphrodite at Aphrodisias E728474 entity
Predicate laterReligionInfluence P120799 FINISHED
Object Roman religion 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: Roman religion | Statement: [Sanctuary of Aphrodite at Aphrodisias, laterReligionInfluence, Roman religion]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: laterReligionInfluence
Context triple: [Sanctuary of Aphrodite at Aphrodisias, laterReligionInfluence, Roman religion]
  • A. laterInfluencedByReligion chosen
    Indicates that an entity was influenced at a later time by a particular religion or religious tradition.
  • B. influencedReligion
    Indicates that one entity has had a shaping or modifying effect on the religious beliefs, practices, or traditions of another entity.
  • C. influencedByReligion
    Indicates that an entity’s characteristics, decisions, or development are shaped or affected by religious beliefs, practices, or institutions.
  • D. laterReligion
    Indicates that one religion or religious affiliation chronologically follows or replaces another for the same entity.
  • E. hadReligionPolicyImpact
    Indicates that an entity’s actions, decisions, or policies had a significant effect on religious practices, institutions, or religious policy.
  • 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_69f0319e8e7c8190b37288c8845b9dbc completed April 28, 2026, 4:03 a.m.
NER Named-entity recognition batch_69fddac4e2f48190a9301d3422658b29 completed May 8, 2026, 12:44 p.m.
PD Predicate disambiguation batch_69fdda06969c8190b5d033964ea2a690 completed May 8, 2026, 12:41 p.m.
Created at: April 28, 2026, 6:42 a.m.