Triple

T1546690
Position Surface form Disambiguated ID Type / Status
Subject Typikon E32992 entity
Predicate appliesTo P1129 FINISHED
Object Matins E142795 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: Matins | Statement: [Typikon, appliesTo, Matins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matins
Context triple: [Typikon, appliesTo, Matins]
  • A. Matins chosen
    Matins is a traditional Christian liturgical service of morning prayer, especially prominent in monastic and Orthodox worship.
  • B. Vespers
    Vespers is an evening prayer service in the Byzantine Rite, marking the liturgical beginning of the day with psalms, hymns, and incense.
  • C. Compline
    Compline is the traditional Christian night prayer service, marking the final liturgical office of the day in various church traditions.
  • D. Shacharit
    Shacharit is the Jewish morning prayer service, featuring core elements such as the Shema and Amidah, recited daily and with special liturgical additions on festivals and fast days.
  • E. The Angelus
    The Angelus is a famous 19th-century painting by Jean-François Millet depicting two peasants pausing in a field for evening prayer, emblematic of rural piety and realism.
  • 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_69a885ed29088190a3c2d5a3d100c16e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa61fc0b5c8190bad34c17c3b46c7e completed March 6, 2026, 5:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad37092b648190a339114ffc37d1db completed March 8, 2026, 8:44 a.m.
Created at: March 4, 2026, 7:26 p.m.