Triple

T37367166
Position Surface form Disambiguated ID Type / Status
Subject Vivarais E927741 entity
Predicate religiousAdministrationCenter P23109 FINISHED
Object Viviers 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: Viviers | Statement: [Vivarais, religiousAdministrationCenter, Viviers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: religiousAdministrationCenter
Context triple: [Vivarais, religiousAdministrationCenter, Viviers]
  • A. religiousAdministration
    Indicates that one entity holds authority or responsibility for managing, overseeing, or governing the religious affairs, practices, or institutions of another entity.
  • B. religiousBuildingManaged
    Indicates that one entity is responsible for overseeing, operating, or administering a religious building associated with another entity.
  • C. ecclesiasticalCenter chosen
    Indicates that a place functions as a primary religious or church administrative hub for a surrounding area or community.
  • D. isMajorReligiousBuildingOf
    Indicates that a building serves as the primary or most significant religious structure associated with a particular religious group, institution, or area.
  • E. tookPlaceAtReligiousCenter
    Indicates that an event or action occurred at a religious center or place of worship.
  • 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_69f76eb820248190a5c395ca50ad002a completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a002103c93081908398fa5726f5fa6e completed May 10, 2026, 6:09 a.m.
PD Predicate disambiguation batch_6a001fcb9fb48190a27d8f2ca983fbe6 completed May 10, 2026, 6:03 a.m.
Created at: May 3, 2026, 4:16 p.m.