Triple

T31450521
Position Surface form Disambiguated ID Type / Status
Subject Debre Libanos Monastery E802308 entity
Predicate hasRelicOrShrine P181786 FINISHED
Object shrine of Saint Tekle Haymanot 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: shrine of Saint Tekle Haymanot | Statement: [Debre Libanos Monastery, hasRelicOrShrine, shrine of Saint Tekle Haymanot]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasRelicOrShrine
Context triple: [Debre Libanos Monastery, hasRelicOrShrine, shrine of Saint Tekle Haymanot]
  • A. containsShrine
    Indicates that one entity includes or has within its boundaries a shrine associated with it.
  • B. hasShrines chosen
    Indicates that one entity contains, hosts, or is associated with one or more shrines dedicated to another entity.
  • C. hasNearbyShrine
    Indicates that one entity is located close to or in the vicinity of a shrine associated with another entity.
  • D. hasShrinesIn
    Indicates that one entity possesses or maintains shrines that are located within the area or domain of another entity.
  • E. hasMainShrineMaterial
    Indicates the primary material from which a shrine is constructed or predominantly made.
  • 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_69f348c678ac81908a2e950867619061 completed April 30, 2026, 12:19 p.m.
NER Named-entity recognition batch_6a016336c58081909c58c5772e6fb488 completed May 11, 2026, 5:03 a.m.
PD Predicate disambiguation batch_6a0160f25d8081909a6aaa375e9850b0 completed May 11, 2026, 4:54 a.m.
Created at: April 30, 2026, 9:12 p.m.