Triple
T31759084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Islam in Romania |
E810631
|
entity |
| Predicate | oldestMosqueLocation |
P154276
|
FINISHED |
| Object | Mangalia |
—
|
NE NERFINISHED |
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: Mangalia | Statement: [Islam in Romania, oldestMosqueLocation, Mangalia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oldestMosqueLocation Context triple: [Islam in Romania, oldestMosqueLocation, Mangalia]
-
A.
isOldestMosqueIn
chosen
Indicates that a mosque is the most ancient or earliest-built mosque within the specified place or region.
-
B.
isLargestMosqueIn
Indicates that a mosque is the largest mosque located within a specified geographic area or jurisdiction.
-
C.
isOneOfTheLargestMosquesIn
Indicates that the subject mosque ranks among the largest mosques located in the specified place or region.
-
D.
oneOfOldestTemplesIn
Indicates that a temple is among the oldest temples located within a specified place or region.
-
E.
hasMosque
Indicates that one entity possesses, contains, or is the location of a mosque.
- 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_69f348e340d48190b780fae618c51464 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:30 p.m.