Triple
T36273578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tinmel |
E892740
|
entity |
| Predicate | mosqueNotableFeature |
P66993
|
FINISHED |
| Object | hypostyle prayer 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: hypostyle prayer hall | Statement: [Tinmel, mosqueNotableFeature, hypostyle prayer hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mosqueNotableFeature Context triple: [Tinmel, mosqueNotableFeature, hypostyle prayer hall]
-
A.
notableMosqueArchitectureStyle
chosen
Indicates that a mosque is characterized by or exemplifies a particular architectural style.
-
B.
hasMosque
Indicates that one entity possesses, contains, or is the location of a mosque.
-
C.
mosqueFunction
Indicates that one entity serves as the religious or communal function or role of a mosque for another entity.
-
D.
mainMosqueCity
Indicates that a city is the primary location of a particular mosque, typically where the mosque is chiefly associated or situated.
-
E.
hasMinaretLikeFeatures
Indicates that something possesses architectural characteristics resembling those of a minaret, such as a tall, slender tower-like form or similar structural features.
- 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_69f76e488f34819083e254dbe288c27a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c475c58c8190a883554231e88c88 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:09 p.m.