Triple

T5331856
Position Surface form Disambiguated ID Type / Status
Subject Great Mosque of Kairouan E123327 entity
Predicate prayerHallType P53929 FINISHED
Object hypostyle hall with multiple aisles 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: hypostyle hall with multiple aisles | Statement: [Great Mosque of Kairouan, prayerHallType, hypostyle hall with multiple aisles]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: prayerHallType
Context triple: [Great Mosque of Kairouan, prayerHallType, hypostyle hall with multiple aisles]
  • A. mainPrayerHallType chosen
    Indicates the specific architectural or functional type assigned to a main prayer hall within a religious or worship-related structure.
  • B. prayerHallCapacity
    Indicates the maximum number of people that the prayer hall is designed or allowed to accommodate at one time.
  • C. templeType
    Indicates the specific category or classification of a temple in terms of its form, function, or religious/architectural style.
  • D. hasMosque
    Indicates that one entity possesses, contains, or is the location of a mosque.
  • E. hasMihrab
    Indicates that a structure or space contains or is equipped with a mihrab, the niche indicating the direction of prayer in a mosque or Islamic prayer area.
  • 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_69bd46477f9081909d242a327d749466 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85aab0308190990626cbc9da3e21 completed March 20, 2026, 5:36 p.m.
PD Predicate disambiguation batch_69bd84583dbc819088a03e3afb30178c completed March 20, 2026, 5:31 p.m.
Created at: March 20, 2026, 2 p.m.