Triple

T29857042
Position Surface form Disambiguated ID Type / Status
Subject Dukhang (assembly hall) E758214 entity
Predicate primaryRoleInMonastery P37071 FINISHED
Object main communal prayer and ritual hall — 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: main communal prayer and ritual hall | Statement: [Dukhang (assembly hall), primaryRoleInMonastery, main communal prayer and ritual hall]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryRoleInMonastery
Context triple: [Dukhang (assembly hall), primaryRoleInMonastery, main communal prayer and ritual hall]
  • A. roleInMonasticism chosen
    Indicates the specific function, position, or status an entity holds within a monastic community or tradition.
  • B. wasMonkOf
    Indicates that a person was a member or monk belonging to a particular religious order, monastery, or monastic community.
  • C. presidingMonk
    Indicates that a particular monk holds the role of leading or overseeing a specific religious ceremony, event, or institution.
  • D. monasteryOrder
    Indicates that a monastery belongs to, follows, or is affiliated with a particular religious order.
  • E. monastery
    Indicates that an entity is or functions as a monastery, typically a religious community or building where monastics live and practice.
  • 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_69f2245b4dec8190b85f664d918a00a5 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_6a019dfc69fc8190b0d80279a6216ba7 completed May 11, 2026, 9:14 a.m.
PD Predicate disambiguation batch_6a019d54586c81908292d4880db9fad2 completed May 11, 2026, 9:11 a.m.
Created at: April 29, 2026, 5:47 p.m.