Triple

T28851472
Position Surface form Disambiguated ID Type / Status
Subject Tarikhaneh Mosque E728606 entity
Predicate hasMihrabOrientation P86711 FINISHED
Object qibla towards Mecca 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: qibla towards Mecca | Statement: [Tarikhaneh Mosque, hasMihrabOrientation, qibla towards Mecca]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMihrabOrientation
Context triple: [Tarikhaneh Mosque, hasMihrabOrientation, qibla towards Mecca]
  • A. 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.
  • B. hasMihrabCount
    Indicates the number of mihrabs associated with or present in a given entity or structure.
  • C. hasQiblaWall
    Indicates that a structure or space possesses a designated qibla wall, i.e., the wall oriented toward the direction of Islamic prayer.
  • D. hasMinaretFeature
    Indicates that something possesses or includes a minaret as one of its architectural or structural features.
  • E. hasQiblaDirection chosen
    Indicates the directional relationship specifying which way one should face (toward the Kaaba in Mecca) for prayer.
  • 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_69f0319f4e5481909e4c439dbe8be940 completed April 28, 2026, 4:03 a.m.
NER Named-entity recognition batch_69f70e8755a48190931eaa77946f9460 completed May 3, 2026, 8:59 a.m.
PD Predicate disambiguation batch_69f70abc00848190a1c3f495ef6c8dc6 completed May 3, 2026, 8:43 a.m.
Created at: April 28, 2026, 6:44 a.m.