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.