Triple

T4144668
Position Surface form Disambiguated ID Type / Status
Subject Fossanova Abbey E89353 entity
Predicate dedicatedTo P500 FINISHED
Object Saint Mary E46518 NE 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: Saint Mary | Statement: [Fossanova Abbey, dedicatedTo, Saint Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint Mary
Context triple: [Fossanova Abbey, dedicatedTo, Saint Mary]
  • A. Saint Mary chosen
    Saint Mary is a central figure in Christianity, revered as the mother of Jesus Christ and honored as a model of faith and purity in numerous traditions and churches worldwide.
  • B. Saint Mary of the See
    Saint Mary of the See is the Marian title under which the Virgin Mary is venerated as the patroness of Seville Cathedral.
  • C. St Marys
    St Marys is a small coastal village on Mainland, the largest island of Orkney in northern Scotland.
  • D. Our Lady of the Assumption
    Our Lady of the Assumption is a Marian title of the Virgin Mary that honors her being taken body and soul into heaven, serving as the patroness of numerous churches and cathedrals worldwide.
  • E. Saint Martha
    Saint Martha is a New Testament figure, sister of Mary and Lazarus, venerated as a saint for her hospitality and service to Jesus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69aed95785788190ae75bcf0cd1cafdf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af025e850c819085ec05b9d9b60712 completed March 9, 2026, 5:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f2e787881908a9721877b0fd4ae completed March 14, 2026, 3:30 p.m.
Created at: March 9, 2026, 3:43 p.m.